**See our complete guide:** [Personalization tactics that actually drive conversions](/blog/personalization-tactics-that-drive-conversions).

---

## What is predictive personalization?

Many brands are familiar with personalization, and the positive impact it can have on your marketing strategy. In recent years, advancements in machine learning and data activation have opened the door for more [authentic personalization at scale](/blog/unlocking-authentic-personalization-at-scale).

Predictive personalization is a term that involves using various machine learning predictions to create customized, personalized experiences for customers, leads, prospects, or any other interesting group of people. It enhances [personalization strategies across the entire customer journey](/blog/personalization-strategies-across-buyers-journey). Whether you’re focusing on–or looking to incorporate–product recommendations, lead scoring, churn prevention, repeat purchasers, or something else altogether, predictive personalization strengthens those strategies and provides clear indicators for how to engage so that every interaction your customers have with your brand is a delight.

## Benefits of using predictive personalization for personalization at scale

On its own, creating personalized content that’s relevant to each individual customer is a long, data-hungry process. Using machine learning for predictive personalization, however, simplifies the process and provides an array of benefits that enable you to achieve personalization at scale.

### Enhanced insights through vivid consumer data

Your first-party customer data includes key data points that describe your people your brand is interested in–your customers, leads, prospects, and more–through their interactions with your brand. This can help you identify the products & services that they’re interested in, so that you can create offers that are relevant to them.

Predictive personalization involves the unification of your first-party customer data with [rich, third-party, cookieless consumer data](/features/data)–after all, your customers exist outside of interactions with your brand. The end-result is a clear 360º view of your customers, leads, prospects, and any other group of people you’re interested in that gives you a firm understanding of who your customers are and what they’re like. [Insights](/blog/how-to-create-a-customer-insight-strategy) via demographics, psychographics, financials, hobbies, and more give you easy guidance for how to personalize your engagement in a highly resonant way.

### Proactive engagement

Regardless of the interaction in question, it’s always better, if given the option, to be proactive rather than reactive. Predictive personalization gives you the ability to personalize your content & creative before you’ve even interacted. You’ll find insights like how likely they are to churn and how much they’re likely to spend via their predicted LTV, so that you’re always one step ahead of the next action your customers are going to take.

[![Predictive personalization mock](/images/blog/predictive-personalization-mock.png)](/images/blog/predictive-personalization-mock.png)

### Personalization at scale

By using machine learning for predictive personalization, the effort involved in scaling personalization across your entire customer base–past, present, and future–isn’t as herculean as it sounds. Machine learning algorithms can segment your customers into bespoke, cohesive personas that you can deploy [anywhere in your stack](/integrations), allowing you to create individualized, personalized campaigns for any given subgroup of people you’re interested in.

### Internal talk track alignment

While the benefits of predictive personalization on external-facing engagement are clear–[see how Sealed did it](/blog/sealed-lead-optimization)–there’s an additional benefit that’s equally as impactful: internal alignment of understanding who your customers are, and what makes them tick. Personas enable you to craft clear talk tracks on a persona-level basis so that, regardless of salesperson, prospects and leads will receive content that highlights the same resonant features. Predictive personalization can also help identify which of your salespeople are best at speaking to specific personas so that you can set priorities and internal coaching appropriately.

## Implementing predictive personalization with Faraday

Customer prediction platforms like Faraday allow you to implement predictive personalization with ease–without a data science degree, and without a single line of code. Let’s dive into Faraday to see just how easy it is.

### Connect data and define customers

First, you’ll map your customer data to the matching Faraday properties. Then, in cohorts, you’ll build a cohort for your [current customers](/docs/cohorts/customers_from_hosted_csv) by defining the event that makes them a customer, such as a purchase.

[![Predictive personalization customers cohort](/images/blog/predictive-personalization-cohort.png)](/images/blog/predictive-personalization-cohort.png)

### Build personas to reveal rich insights to enable predictive personalization

Predict personas with the help of Faraday’s rich, cookieless, opt-in consumer data on top of your own first-party customer data. Discover trait breakdowns like hobbies, shopping styles, gender, household income, and more to understand the nuances of how different portions of your customer base stand apart from each other. These breakdowns give you crystal-clear guidance on how to speak to your customers in a way that makes them feel understood.

[![Predictive personalization customer personas](/images/blog/predictive-personalization-personas.png)](/images/blog/predictive-personalization-personas.png)

### Use customer predictions to create proactive, relevant campaigns

Take predictive personalization to the next level by predicting likelihood to churn, repeat purchase, and more so that your content is not only personalized to match who your customers are, but that it’s also attuned to how they’ve interacted with–or _will_ interact with–your brand, and at any scale you need, wherever in your stack you need.

**Ready to try predictive personalization out? [Create a free account](https://faraday.ai/signup).**

Explore the benefits of predictive personalization & the impact it can have on your marketing strategy through rich, effective customer insights.

Predictive personalization: Using machine learning to personalize customer experiences

**See our complete guide:** [How Faraday validates predictions — and how you can too](/blog/holdout-testing-with-faraday).

---

If you've ever used AI to make predictions, chances are you've asked yourself "How do I know these are . . . correct?" It's a fair question, and healthy skepticism is a critical component of any Responsible AI practice.

Luckily there are plenty of great options for confirming that the predictions you're getting are mostly right. First, a bit of background.

## Prediction basics: How do AI models make predictions?

To set the stage, let's review how prediction works. Throughout this post, I'll use the example of a company wanting to predict which of its leads are most likely to "convert" (become a customer). In Faraday you'd represent this prediction objective with an outcome like so:

![Lead conversion outcome configuration](/images/blog/testing_predictions/outcome.png)

### Finding patterns

Now we'll take you behind the scenes. To predict something, a system must comb through historical examples of that thing happening to find patterns.

Once you know the patterns, you can compare newly observed behavior to the crucial patterns that signal "true" - if they are similar, you predict "true," otherwise "false."

So, to follow our example, the first step is to pull together some historical lead data, including some leads that converted and some that didn't.

![Training data diagram](/images/blog/testing_predictions/training_data.png)

Here, the top row represents your leads over time at their first capture point. Some of them—the **<span style={{color: "green"}}>green</span>** dots—"convert" by becoming customers: we call these _examples_. Others—the **<span style={{color: "red"}}>red</span>** dots—go "stale" and represent failures: we call these _counterexamples_. It's too early to say what the few remaining gray dots will do, so we'll just ignore them.

One useful thing to note is that 6/13 of our leads converted, or about half the time. This will come in handy down the road.

Your prediction system will then use one of a variety of methods to look for interesting patterns. Is there something in common among the green leads? What about the red ones? How are they different? This identification of patterns (the model) is what lets the system make predictions about new leads.

### Using patterns to make predictions

So now, let's take those pesky remaining gray dots, as well as some new ones that might have popped up since we figured out our patterns. I've put a dark border around them:

![Data diagram including new leads](/images/blog/testing_predictions/new_leads.png)

Your prediction system will scrutinize each of these possibilities to see which patterns in your list it follows. If it follows a lot of the patterns associated with conversion, the system will predict that it will convert. If it follows a lot of the patterns associated with non-conversion, the system will predict non-conversion.

![Diagram showing predictions](/images/blog/testing_predictions/prediction.png)

### Beware silly patterns

Easy, right? Too easy you might say. The reason to be skeptical here is that the patterns your prediction system found may be coincidences rather than reflect some underlying truth.

For example, your prediction system may say:

> Here's a pattern I found! Leads with one of these exact email addresses convert, all others don't: `amy@example.com, leon@example.com, ..., pat@example.com`

Sounds silly, but it happens all the time when the wrong kind of data is examined for patterns. The methods your prediction system uses aren't always clever enough to distinguish between goofy patterns and serious ones. Based on the data available, this pattern is actually incredibly powerful! In fact, it's 100% accurate.

Problem is, it will never work with any new leads, because they'll all have different email addresses and the system will therefore predict non-conversion for all of them.

## Three holdout testing methods to see if your predictions are accurate

The way to avoid this kind of silliness is to "test" your patterns to see if they're right. If they pass the test, you can trust them going forward.

Think about your tests in school: your teacher asked you questions and you provided answers. Your teacher knew the true answers. If your answers matched the teacher's true answers, you got an A.

The hardest part of all this is that somebody has to "know" the "true" answers. If only we had some lead data where we knew the right answer . . .

But of course we do! We know which leads actually converted and which didn't. We just can't use the _same_ data to both find patterns and put those patterns to the test.

There are a few great ways to split up your data for these two simultaneous purposes. They all rely on a "holdout"—setting aside a portion of the data to use exclusively for testing. This allows you to see whether the system "understands" enough to assess new data versus only being able to regurgitate answers for the questions it has already seen. Let's dive into these methods now.

### Method 1: random holdout

#### Setup

This is the most common approach, and it involves choosing a random subset of your historical data to set aside as a holdout. Only then do you use your prediction system to find patterns among the remaining data.

![Cross validation diagram](/images/blog/testing_predictions/random_holdout.png)

Here, we've used 50% of our data as a holdout. The system will find patterns exclusively among the remaining leads.

#### Testing

Now we're ready to "take the test." The leads in the holdout are the questions, and their true disposition (converted or not) is the answer key. But for the time being we pretend we don't have the answer key and we treat the holdout leads like new leads. What can the patterns we have tell us about these leads?

I'll illustrate those predictions with colored borders on the holdout leads:

![Prediction step of cross validation](/images/blog/testing_predictions/random_holdout-prediction.png)

Once we've used the patterns to make predictions about the holdout leads, we can dramatically reveal the answer key and see how accurate the patterns really are. Let's see how we did:

![Cross validation results](/images/blog/testing_predictions/cross_validation.png)

We got 4 right and 2 wrong for about 67% accuracy. Is that good or bad?

#### Evaluation

In real life you'll rarely get an A on this test. In some cases you'll predict conversion when the lead didn't actually convert (false positive). In other cases, you'll predict non-conversion when the lead did actually convert (false negative).

Recall that our actual lead conversion rate is about 50%. That means that a really dumb prediction system could always predict "convert" and get it right about 50% of the time, or flip a virtual coin and get the same result. By this measure, 67% is quite a bit better!

So assuming you got more right than wrong, it's an improvement. Before, your patterns were always right about your historical leads, but were useless for assessing new leads. Now, maybe your patterns aren't as perfect, but at least they're useful!

#### Conclusion

Finding the right balance between false positives and false negatives is part of the art of prediction and ultimately comes down to risk versus reward. It's out of scope for this post but I'll be writing one on that soon—subscribe below to get notified.

The upshot here is that the patterns the system found on the non-holdout leads appear to be effective in making predictions about the holdout leads. This is a very good sign that the patterns themselves are "real" and not based on silly coincidences.

The name for this approach is _cross-validation_. In practice, you actually perform this random holdout method multiple times to _really_ make sure your patterns are real. The Faraday platform automatically uses 3 passes like this every time we look for patterns.

### Method 2: recent holdout

#### Setup

Another approach is to use your most recent data as your holdout, a method called a _backtest_. As a refresher, here's what we started with:

![Training data diagram](/images/blog/testing_predictions/training_data.png)

To use this method, we temporarily "rewind" time to a previous day, like so:

![Rewound training data diagram](/images/blog/testing_predictions/recent_holdout.png)

From here, the process is much like above. Our prediction system attempts to find patterns looking backwards from our "pretend now," ignoring the lead data that has transpired since then, which becomes the holdout.

#### Testing

Then it uses those "old" patterns to examine recent leads. Again, predictions here are represented by the colored borders on the holdout leads:

![Backtest prediction step](/images/blog/testing_predictions/recent_holdout-prediction.png)

And finally we use our answer key to see how we did:

![Backtest results](/images/blog/testing_predictions/backtest.png)

#### Evaluation

Here again, we went 4 for 6, or 67%. By the same logic as above, not bad.

The big advantage of the recent holdout versus the random holdout in my mind is that it's easier to understand and, ultimately, trust.

The main disadvantage of this type of holdout is the system can only look for patterns within data spanning a shorter period of time, so if the important patterns take time to appear, then using a recent holdout won't perform as well as using a random holdout.

Faraday has this feature built in as an additional option if you want it, although it's very compute-intensive so it's not available on all accounts by default. If you don't see it and want to use it, just ask support.

### Method 3: secret holdout

You may hear other folks call this a blind holdout, although I hope to see the end of that ableist terminology soon.

The idea here is that you go to extreme lengths to hide your holdout from the prediction system—or even the company running the prediction system!—in order to boost your confidence even further.

Here, the principal doesn't even trust the teacher with the answer key! The diagram looks something like this:

![Secret holdout](/images/blog/testing_predictions/secret_holdout.png)

The user has pre-emptively removed a random portion of the data to serve as the holdout and shared the remainder with the prediction system, which has no idea what's in the holdout.

The system finds patterns using all the data it has. Then the user performs the test by presenting the holdout leads to the system _without their true dispositions_. The system makes its predictions as usual:

![Secret test prediction step](/images/blog/testing_predictions/secret_holdout-prediction.png)

The user then secretly compares these predictions to the "true" answer key to determine accuracy.

In practice the secret holdout is exactly the same as the random holdout, just a heck of a lot more complicated and time-consuming. Nevertheless, you could consider it if you don't trust your prediction system for one reason or another.

Faraday supports secret holdout testing. When connecting your data, make sure to remove your holdout first, so Faraday never sees it. Configure your account as usual. Then upload your holdout—minus disposition—as a CSV dataset with a `holdout` trait, create a matching **Holdout** cohort, and use it as a the population in a new pipeline. Add the outcome you want to test to the payload, and deploy an identified CSV target. Now match Faraday's predictions back to your original holdout and analyze to evaluate accuracy.

## The real deal

Prediction systems finding silly patterns is a real problem—you could even say it's _the_ problem of machine learning. Luckily there are lots of ways to avoid these kinds of shenanigans, and good prediction systems employ them automatically.

Behind the scenes, Faraday runs random and/or recent holdout testing constantly to confirm it's finding legitimate patterns that are practically useful going forward.

I know all this (I helped build the system!), but I still treasure my ongoing skepticism, and you should too. Hopefully understanding how pattern validation works, and seeing how it operates behind the scenes, will help you develop a careful confidence in the predictions you build your workflows around.

Three holdout testing methods you can use to evaluate the accuracy of a model’s predictions.

How to set up holdout tests to evaluate prediction accuracy

The renewable energy sector is growing rapidly as consumers and businesses increasingly turn to sustainable solutions. While this growth presents a wealth of opportunities, it’s also been a bumpy ride, with market uncertainties and shifting dynamics creating challenges for providers. In this ever-changing landscape, success hinges on the ability to identify, prioritize, and place their bets on the right horse—or, in this case, the consumer segments with the most value-generating potential.
When a prominent solar energy provider faced this challenge in 2024, they realized that finding the best answer alone wasn’t necessary, or the best use of their specialized team’s energy. Instead they turned to Faraday.

## The problem: they were tired of guessing and wanted to make data-driven decisions they could feel confident in

This solar company faced a wide-ranging set of problems as they tried to grow their sales pipeline in 2024. Although they were determined to scale efficiently and outpace competitors, their existing targeting approach lacked precision, which led to wasted marketing spend in low-potential areas and with the wrong consumers. Additionally, they were overwhelmed by an abundance of raw data that made it difficult to derive actionable insights. Finally, rapid market growth had also attracted competitors, heightening the urgency for smarter acquisition strategies.

These challenges translated into tangible pain points like lower conversion rates, wasted time, and inefficient marketing spend. Without a clear roadmap to identify and prioritize high-potential customers, their ability to compete effectively in the fast-evolving solar market was under threat.

## The solution: Faraday’s predictive analysis tools gave them data driven answer and confidence

Realizing these challenges could hinder their growth, the company decided to seek outside expertise and while these problems might seem insurmountable, they’re what we get up for.

Almost immediately after onboarding and hearing about their issues, we identified two significant ways we could support their expansion goals and help them to better understand their market: Persona Analysis and Market Opportunity Analysis.

### Persona Analysis

Faraday’s [Persona Analysis](/templates/thematic-personalization) is a process that helps companies uncover the traits and behaviors most closely associated with their ideal customers. By analyzing first-party data from the client as well as rich third-party data from our proprietary [Faraday Identity Graph](/features/faraday-identity-graph), we create detailed profiles of a company’s highest-value personas. These represent distinct socio-demographic groups that share common characteristics and behaviors, making it easier to design marketing strategies tailored to their specific needs.

For this solar provider, Persona Analysis revealed the unique traits that drive solar adoption. By understanding these factors, the company could refine its messaging, focus on the most relevant customer segments, and craft outreach strategies that resonated with their target audience.

But that on its own might not be enough. This tools allows us to know what _type_ of person to target, but not necessarily how many of them exist and are reachable

### Market Opportunity Analysis

That’s where [Market Opportunity Analysis (MOA)](https://faraday.ai/blog/unlocking-growth-with-market-opportunity-analysis) comes in. Building on these insights and persona profiles, Faraday conducted a comprehensive Market Opportunity Analysis, a process which combines the client’s first-party data with broader market trends and dynamics to quantify their existing market. To conduct this analysis, Faraday builds a complex and individualized predictive model which compares that quantified market to the population at large, represented through [Faraday’s Identity Graph](https://faraday.ai/features/faraday-identity-graph)—a robust and proprietary dataset containing detailed information on nearly every U.S. adult. This enables the identification of the totality of potential new customers who resemble the company’s top-performing personas available in the U.S. An example is pictured below.

![Example of our Market Opportunity Analysis](/images/blog/moa_map.png)

The analysis doesn’t stop there though. It then visually maps these high-potential customers by state, zip code, and even down to the individual level. These dynamic predictions enable clients to focus on specific regions and neighborhoods with the highest concentration of ideal customers. These insights are paired with additional predictive tools, such as lead routing and direct mail targeting, ensuring marketing efforts can be directed with precision and confidence.

Through this dual approach, the solar provider gained actionable insights about market potential and customer behaviors. These findings informed advertising campaigns, local outreach initiatives, and third-party logistics strategies, enabling the company to allocate resources strategically and maximize their impact.

## The results

The impact of Faraday’s Persona and Market Opportunity Analysis changed the company’s entire outlook. Where as before, they had marketed broadly based on vague demographic factors, they could now target their spend down to the top zipcodes, and even to the individuals most likely to convert, suggesting products that were more likely to sell and talking to their ideal consumer in a way that they were most likely to respond to.

A particularly telling example of the power of these tools came when the solar provider, who primarily relies on their installation trucks for marketing, discovered through Market Opportunity Analysis that some of the highest-potential zip codes were in rural areas—places where the trucks wouldn't typically reach. To ensure these high-fit prospects were engaged, they decided to run a targeted direct mail campaign in those regions, making sure they could be seen by the people who mattered most.

Faraday's tools didn’t just provide actionable data—they gave the solar provider the confidence to act without hesitation. In this case that meant switching up their marketing strategy significantly. By moving away from broad, guesswork-based targeting, they were able to focus their efforts and dollar specifically on high-potential customers and this makes all the difference.

## Conclusion

Faraday's persona and market opportunity analysis provided clarity that allowed the company to make informed decisions on where to invest their resources, cutting out low-value areas and optimizing their target audience. With the right data guiding them, they gained the confidence to expand in competitive markets and scale efficiently. This success story underscores the value of data-driven insights in driving market expansion and delivering long-term success.

What's next for them? We're going to predict (with _high confidence_) more sales\!

Using Faraday's predictive tools, this company transformed their marketing strategy by targeting only the highest-potential customers.

How a leading solar provider improved customer targeting with personas and market opportunity analysis

## What is direct mail marketing?

Direct mail marketing is the act of a brand engaging with its customers and prospects through physical mail. It can come in various forms, from postcards, to letters, to branded water bottles, and everything in between. The most effective direct mail campaigns are highly personalized to resonate with a brand’s customers. Before email and digital engagement became the norm, direct mail was one of the best ways to reach your customers. While digital has since pushed direct mail marketing to the side, it’s had a resurgence in recent years because, in the age of digital media, personalized direct mail _stands out_–assuming you’ve done your due diligence and personalized it appropriately to match your customers’ wants and needs. Take [PostcardMania](https://www.postcardmania.com/blog/direct-mail-statistics-2023) for example, who has seen their revenue grow 17.56% each year post-pandemic in comparison to 4.67% pre-pandemic.

## Benefits of personalized direct mail

Personalized direct mail has a variety of benefits over digital to prove that it’s a great supplement to your engagement strategy. To start, the response rate of direct mail marketing is 9%, in [comparison](https://www.postgrid.com/direct-mail-statistics/) to the 1% of email, paid search, and social media. Additionally, it has a 29% ROI compared to 23% for paid search and 16% for online display. The benefits of personalized direct mail stem from two key features:

The first is that personalized direct mail can be tailored to a greater extent than its alternatives. Say that you know a group of your customers are avid runners that regularly buy running gear from your store. A digitally-focused brand might launch a campaign between major purchases for that group of people, where they want to offer them a free water bottle for being a loyal customer. An email offering the freebie will look a lot like other emails they receive, so it’ll likely be discarded, even if it’s genuine. With a brand savvy in personalized direct mail, the water bottle could be at their doorstep–delivered in a box personalized with running-focused creative–then in their hands as it becomes their daily drinker that they freely advertise for you.

The second is that, in the digital age, people are used to receiving all manner of marketing emails, to the point that it’s almost second nature to mark something as spam, or delete it. Personalized direct mail is more distinctive, and is much more likely to be seen by your customers. After all, 77% of people sort their physical mail immediately [according](https://www.pb.com/docs/US/pdf/Microsite/Nonprofit/ed_np_getyourmailopened_05MailMoment.pdf) to the USPS. With a chance that high for your mail to be seen, making use of personalized direct mail that resonates with your customers is the key to standing out.

## How can direct mail be personalized?

Personalized direct mail can be accomplished through several different means that utilize your first-party data, such as merge tags and creative variations. With machine learning and third-party consumer data on top of your first-party data, you can accomplish it more effectively, and at scale.

### Leverage data and machine learning for insights to guide personalization

To start, your customer data needs basic identifiers, like name and address, so that you know where to send your personalized direct mail. On top of that, you need to leverage all of your first-party engagement data, like products purchased, abandoned carts, subscriptions, and so on, to ensure any offers you make are relevant. You wouldn’t want to find a postcard with a discount in your mailbox for cat food when you don’t own a cat, would you?

Regardless of how strong your first-party data is, it provides limited insight into who your customers are beyond their interactions with your brand. With [rich, third-party consumer data](https://faraday.ai/features/data) that includes demographics, psychographics, lifestyle, financials, and more, you can take your segmentation to the next level, enabling you to customize your copy & creative so that it resonates.

In addition to leveraging both first-and-third-party data, using machine learning to identify distinct groups–personas–allows you to create personalized direct mail at scale, with each group can be targeted with its own resonant, relevant engagement.

### Use insights to inform your personalization

A uniquely powerful way to personalize direct mail is to make use of merge tags. With merge tags, you can personalize on an individualized basis so that any data you have that’s relevant to your customers can be utilized. This way, beneath the persona-level segmentation, your personalized direct mail is dynamic enough to include data points like, say, someone’s name, subscription level, or the city they live in. On top of that, if you have physical locations, merge tags can be used to point customers to your nearest storefront.

Personas also enable distinct creative variations that are relevant to each persona. For your Exercise Guru Elayne persona, you could include imagery of women running alongside a dog and while pushing a stroller, because the majority of the persona are dog owners and have children in the household.

Take your personalized direct mail even further by adding customized product offers and discount codes that are relevant to each persona. Maybe, utilizing your customer data, you know that a specific group of your customers have already purchased a pair of running shoes. You know they won’t need another pair for a while, so a promo for that will bounce off. An offer for a pair of running socks or shorts, on the other hand, is more likely to catch their attention.

![Postcard with personalized discount](/images/blog/direct-mail-discount.png)

_Image via [TheMailShark](https://www.themailshark.com/product-samples/postcards/)._

## Pillars of a personalized direct mail strategy

There are three pillars to a successful personalized direct mail strategy.

- **Insights**: Identify distinct customer segments and their related insights by generating [AI-powered personas](https://faraday.ai/predict/category/persona_assignments). Through these insights, you have clear indicators for how to engage your customers and leads in ways that are highly resonant with their lifestyles.
- **Customization**: Determine how you’ll customize direct mailers based on your insights, data, and promotions. The most impactful personalized direct mail campaigns will include a mix of products, imagery, discounts, and merge tags, ensuring you’re including the right content. Brands that offer personalized direct mail services, provide a range of these types of services.
- **Targeting**: The cost of direct mail can add up–especially if you’re not targeting the best fits. Predict for likelihood to [buy](https://faraday.ai/predict/category/likely_buyers), [convert](https://faraday.ai/predict/category/lead_scores), [repeat purchase](https://faraday.ai/predict/category/repeat_purchasers), [churn](https://faraday.ai/predict/category/churn_scores), or any other relevant data point so that you’re spending your time and money where they matter most.

## How to implement a personalized direct mail strategy with Faraday

With a customer prediction platform like Faraday, you can identify personas to gain rich insights and predict behaviors so that you can deliver resonant, personalized direct mail to likely-to-act audiences. All it takes is some historical data about your customers. Here’s how it works.

### Connect data and define customers

To start, you plug in your data by mapping your data fields to Faraday properties.

[![Direct mail dataset](/images/blog/direct-mail-dataset.png)](/images/blog/direct-mail-dataset.png)

Then, in cohorts, you’ll utilize both your customer data and Faraday’s rich, built-in consumer data to build the exact [cohort](https://faraday.ai/docs/cohorts/customers_from_hosted_csv)–or interesting group of people–you want. In Faraday, you’ll create a cohort for your customers so that you can find more people like them, and you’ll also build a cohort of people with mailable addresses, so that you’re also targeting unknown audiences. You'll do this by choosing the following traits when building a cohort:

- **Record quality code**: one of: mailable

[![Faraday direct mail cohort traits](/images/blog/direct_mail_guide/direct-mail-guide-cohort-traits.png)](/images/blog/direct_mail_guide/direct-mail-guide-cohort-traits.png)

### Predict personas to reveal rich insights

While you likely have customer data that indicates, in some ways, who your customers might be, predicting personas tells you who they really are, and what makes them tick. Dive into trait breakdowns like age, gender, household income, hobbies, and more–each one guiding you toward engaging with the right messaging.

[![Direct mail persona set](/images/blog/direct-mail-personas.png)](/images/blog/direct-mail-personas.png)

### Predict propensity to buy to target best fits

Next, you’ll build your predictive outcome by defining your attainment cohort as your customers, as that’s your prediction’s finish line–you want more people like your customers. In this example, we’re defining the propensity to buy, or the likelihood that anyone in the U.S. is going to become a customer by making a purchase, but you can predict for virtually any action that someone is likely to take, such as a conversion, repeat purchase, or churn.

[![Direct mail outcome](/images/blog/direct-mail-outcome.png)](/images/blog/direct-mail-outcome.png)

With your prediction defined, create a pipeline to make them actionable by choosing your **likely buyers outcome**, your **persona set**, and your **mailable cohort**.

[![Direct mail pipeline](/images/blog/direct-mail-pipeline.png)](/images/blog/direct-mail-pipeline.png)

Faraday’s machine learning algorithms then predict how likely people are throughout the U.S. to buy your product, while also revealing which people belong to what persona on an individual basis.

### Deploy personalized direct mail predictions to your stack

Likely buyer scores revealing your best fits across the country? Check. AI-generated personas providing clear guidance for personalization? Check. With these insights in-hand, deploy them anywhere in your stack you need them–for example, to a direct mail provider–then, design your copy & creative so that it caters to the personas you’re engaging with.

**Ready to try it out? [Create a free account](https://faraday.ai/signup).**

Learn the benefits of personalized direct mail marketing, how to personalize your direct mail campaigns, and how to use predictive analytics to maximize impact.

Personalized direct mail: How can direct mail be personalized at scale?

Imagine you’re leading a growing retail business with 25 thriving locations. Now, it’s time to decide where to open the next five. Do you expand into an emerging market where demand is heating up, or double down on your presence in regions where your brand is already well known? Is there some other critical factor you haven’t considered? The stakes are high, and even seasoned executives can fall prey to personal biases.

Take, for example, a story we recently heard from a client about an experienced restaurant CEO who was set on opening a location in his beloved hometown—a move driven by emotion rather than data. Fortunately, his team knew to assess the market, which revealed the location wasn’t actually viable. While this upended their original plan, it ultimately saved them the effort and cost of opening a doomed restaurant. This story highlights how critical these decisions are for sustained growth and why relying on data-driven insights (from the beginning) is essential to avoid costly missteps and make confident, strategic choices.

At Faraday, we understand the challenges businesses face when it comes to making strategic growth decisions. That’s why we offer **market opportunity analysis (MOA)**, a powerful tool that helps you confidently identify actionable opportunities that are backed up by data.

## What is market opportunity analysis?

MOA equips your team with a clear understanding of your current market reach and untapped potential. By analyzing your existing customer data and comparing those data points to the population at large, we can help you pinpoint exactly where the next big opportunities lie. Whether you're looking to expand geographically, target new customers, or optimize product offerings, our approach ensures your growth is backed by solid insights.

## How it works at Faraday

MOA provides your team with a data-driven roadmap to your most valuable and actionable growth opportunities, but how does it actually work? Here's how we approach it:

![](/images/blog/moa_analysis_diagram.png)

First, we conduct a detailed assessment of your current market penetration. By analyzing your existing customer base, we identify key traits such as purchasing behaviors, regional preferences, and lifetime value to create an ideal customer profile. Then, leveraging data from the [Faraday Identity Graph (FIG)](https://faraday.ai/features/faraday-identity-graph), we develop a tailored predictive model to evaluate the broader U.S. market and identify prospective customers who closely match your existing audience. This allows us to quantify the untapped potential within the customer segments most likely to drive growth.

Once we’ve identified the high-potential customer segments, we dig deeper into the specific opportunities within those groups. This involves determining which product or service offerings are best suited to each persona to maximize their lifetime value. We also take a close look at geographic trends, mapping out areas where your target customers are most concentrated from the regional level all the way down to zip code, metro area, or even postal route. This data empowers businesses to strategically allocate resources with significantly more confidence and precision than before.

## Unleashing the power of the Faraday Identity Graph (FIG)

A comprehensive MOA requires access to a detailed dataset of the broader population to serve as a benchmark for comparison. Fortunately, Faraday’s **Faraday Identity Graph (FIG)** provides exactly that, and much more. With rich data on nearly all American adults, the FIG offers a robust and comprehensive view of the population, significantly enhancing the reach and depth of our MOA.

The FIG goes beyond basic demographic information, offering nuanced insights into consumer behaviors, preferences, and buying patterns. By tapping into these granular details, businesses can understand their target market in a way that’s far more accurate and actionable than with competing data sources.

## Ready to explore what's next?

MOA can greatly benefit businesses by identifying high-potential customer segments and emerging market trends. By understanding where the highest-value opportunities lie, companies can optimize their marketing strategies and resources, focusing on areas with the highest growth potential. This leads to more targeted and personalized campaigns, which can improve conversion rates, enhance customer engagement, and increase profitability. MOA additionally provides companies with the confidence to know that their strategies are backed by data.

Growth doesn't happen by chance. With Faraday's MOA, you can take the guesswork out of targeting strategy and focus on results. Contact us today to discover how we can help unlock your business's full potential.

MOA empowers businesses to make strategic growth decisions by uncovering untapped potential and high-value opportunities in their market.

Unlocking growth with market opportunity analysis (MOA)

In the world of machine learning, we often encounter two important concepts: the raw propensity score and probability. Though they may sound similar, they represent distinct aspects of a machine learning model's predictions.

## Example of propensity scores vs predicted probabilities

Imagine you have a model that predicts whether it will rain tomorrow. The raw propensity score is like the model's initial hunch or gut feeling about the outcome. It's a numeric value that the model calculates based on various factors like historical weather data, humidity, temperature, and more. The [propensity](https://faraday.ai/blog/propensity-models-predict-customer-behavior) score indicates how likely the model thinks it will rain or not. However, the propensity score itself doesn't give us a clear understanding of how confident the model is in its prediction.

This is where [probability](/blog/faraday-probability-scores) comes into play. The predicted probability aims at providing an answer to the question “how likely is the prediction?” It represents the likelihood of a particular outcome occurring. For example, a score of 0.75 for rain means the model is fairly confident it will rain tomorrow. However, a probability of 0.75 indicates that there is a 75% chance that it will rain tomorrow.

In summary, the raw propensity score is the model's initial guess, while probability quantifies the model's confidence in that guess. Understanding this difference can help us interpret machine learning [predictions](/features/predictions) and make better-informed decisions based on the model's level of certainty.

## Understanding model calibration

The model calibration process refers to the alignment between a model's predicted probabilities and the actual likelihood of events occurring. A good calibration ensures that the predicted probabilities are close to the true theoretical probabilities. Not all machine learning models are perfectly calibrated after training. Some models might be overconfident, providing probabilities that are too extreme, while others might be underconfident, consistently underestimating or overestimating probabilities.

### Importance of model calibration

Calibration is crucial because it impacts decision-making. If a model is well-calibrated, we can trust its probability estimates and use them to make informed choices, such as whether to take an umbrella based on the probability of rain.

Calibrating a model involves post-processing its probability scores to bring them in line with the true probabilities. Various calibration techniques can be employed, such as Platt scaling or isotonic regression, which adjust the raw propensity scores to produce well-calibrated probabilities. These techniques are typically applied during model validation and fine-tuning to ensure that the model's predictions are more accurate and reliable.

The calibration process ensures that when the model predicts a probability, it reflects the true likelihood of the event occurring. For example, if a model predicts a 70% probability of rain, it should be accurate in approximately 70% of the cases where it makes that prediction.

In summary, model calibration in machine learning is all about making sure a model's predicted probabilities accurately reflect the real-world likelihood of events happening. A well-calibrated model is more reliable and can lead to more effective decision-making.

## Benefits of using predicted probabilities

Using predicted probabilities instead of raw propensity scores offers several significant benefits that enhance the interpretability, decision-making, and overall performance of the models:

### Interpretability

Predicted probabilities provide a more intuitive and understandable representation of a model's output. Raw propensity scores are often abstract values that lack clear context, while probabilities are easily interpretable as the likelihood of an event occurring. This makes it easier for stakeholders and end-users to comprehend the model's predictions and build trust in its results.

### Uncertainty quantification

Predicted probabilities convey the model's level of certainty about its predictions. Models can provide probability scores ranging from 0 to 1, indicating their confidence in the predicted outcomes. This uncertainty quantification is valuable in decision-making, as it allows users to consider the risk associated with a prediction and adjust their actions accordingly.

### Threshold selection

Predicted probabilities offer flexibility in choosing decision thresholds. Depending on the specific application and requirements, decision-makers can adjust the probability threshold for classifying positive and negative outcomes. This adaptability allows for a fine-tuning of the model's behavior to suit the desired trade-offs between false positives and false negatives. For example, in the case of a lead conversion, a profitability threshold can be established by taking into account cost of acquisition for each lead, expected profit from actual customers, and probability of conversion.

### Calibration and reliability

When models are well-calibrated, predicted probabilities accurately reflect the real-world likelihood of events. Calibrated probabilities provide more reliable estimates, leading to improved decision-making and better performance in critical applications.

### Ensemble and stacking

Predicted probabilities facilitate model ensembling and stacking techniques. By combining the probabilities from multiple models, ensemble methods can often yield better overall performance compared to individual models or raw propensity score-based approaches.

## Benefits and drawbacks of raw propensity scores

Using raw predictions from models instead of calibrated scores has its own set of pros and cons. Let's explore them.

### Pros of using raw propensity scores:

**Simplicity and Speed**: Raw predictions are the direct output of the model without any additional post-processing, making them easier and faster to obtain. In real-time applications or scenarios where efficiency is critical, using raw propensity scores can be advantageous.

**Suitable for Ranking**: Raw propensity scores can still be useful for ranking predictions. Even though they may not directly represent probabilities, they can help rank instances based on their likelihood of being a positive or negative outcome, which is often sufficient in certain applications.

### Cons of using raw predictions:

**Inconsistent Ranking**: Raw propensity scores might not consistently reflect the true likelihood of events occurring. Two instances with similar raw propensity scores might have significantly different actual probabilities, leading to inaccuracies in ranking and decision-making.

**Suboptimal Decision Thresholds**: Using raw predictions often means relying on fixed decision thresholds (e.g., 0.5 for binary classification), which might not be suitable for all applications. This can lead to suboptimal trade-offs between precision and recall.

**Misinterpretation of Scores**: When raw propensity scores are not calibrated, users might incorrectly interpret them as reliable probabilities, leading to misguided decisions and a lack of trust in the model's predictions.

In summary, while using raw predictions can be straightforward and computationally efficient, it comes with the trade-off of lacking calibrated probabilities and potential inconsistencies in ranking. In many real-world applications, calibrated scores are preferred as they provide interpretable probabilities, better decision thresholds, and improved trust in the model's predictions.

## When should you use propensity score percentiles vs. predicted probabilities?

In the field of machine learning, the choice between using percentiles and probabilities depends on the specific context and the nature of the problem being addressed.

### Using propensity score percentiles

**Outliers are important**: If you are concerned about extreme values or outliers in your data, percentiles can be more robust in representing the distribution. For instance, the 95th percentile captures the value below which 95% of the data lies, making it less sensitive to extreme values.

**Data skewness**: When dealing with heavily skewed datasets, especially those with long tails, percentiles can be more informative than probabilities. Percentiles provide a clearer understanding of the data's spread and central tendencies, even in the presence of skewed distributions.

**Interpretability**: Percentiles can be easier to interpret and explain to non-technical stakeholders. For example, stating that a value is at the 75th percentile means that it is higher than 75% of the other values in the dataset.

### Using predicted probabilities

**Well-calibrated predictions**: Probabilities are essential when you need calibrated predictions. If you want reliable estimates of the likelihood of certain events, probabilities are more suitable. Well-calibrated models can provide accurate and informative probabilities for decision-making.

**Decision thresholds**: In many applications, using probabilities allows you to set appropriate decision thresholds based on your specific needs. For instance, in medical testing, you might want to set a higher threshold to prioritize precision over recall, depending on the consequences of false positives and false negatives.

**Uncertainty quantification**: Probabilities are crucial for quantifying uncertainty around predictions. Confidence intervals and prediction intervals can be constructed using probabilities, giving a range of likely outcomes.

**In summary, use percentiles when you need robust representation of data distribution and are concerned about outliers or skewed data. On the other hand, use probabilities when you require calibrated predictions, decision thresholds, and uncertainty quantification, especially in the context of machine learning models.**

**Ready to try Faraday? [Create a free account](https://faraday.ai/signup).**

Propensity scores and predicted probabilities represent distinct aspects of a machine learning model's predictions. Understand the difference and when you should use them.

Propensity vs probability: Understanding the difference between raw scores and probabilities

Faraday’s data science team has made significant improvements to the accuracy and interpretability of customer predictions within the platform; we’re going to give you a peek under the hood at how Faraday predictions are made.

The data science team introduced a process called **model calibration**, which measures how well the model's predictions match the actual outcomes. This method of calibration results in **probability scores**; predictions that are even more accurate and easier to interpret. Let’s take a look at a model report to break down the changes.

## Lift and precision before model calibration

In the below **pre-calibration** graphic, note the large dip in the lift curve (red arrow). With this lift curve, the top deciles of propensity scores, or the people you’d generally be targeting with a marketing campaign based on these results, have lower lift in the population (green square), indicating that there’s room for improvement.

A lift curve with strong predictability should show a more gradual dip than you see below. Similarly, the positive attainment cohort _home and living_ (blue square)–or the outcome you want to predict for–is very close to 50%, which could also be improved through model calibration. This would result in pipeline deployments having, say, a Jane Doe with a 0.8 score that could be interpreted as _pretty likely_ to achieve the outcome.

[![Image of Faraday model report lift table pre-calibration](/images/blog/probability-pre-calibration.png)](/images/blog/probability-pre-calibration.png)

_The above graphic displays a predictive [model report](/blog/faraday-model-reports) pre-calibration. Model reports can be found in an outcome's analysis view_.

Because Faraday uses multiple predictive models to create an outcome, it makes more sense to compare scores across models rather than treat scores from different models equivalently.

## Lift and precision with model calibration

Now, with model calibration implemented in the below graphic, the lift curve’s dip (red arrow) is much less significant for the top deciles, resulting in an outcome that has a higher positive attainment (blue square) in _home and living_.

[![Image of Faraday model report lift table post-calibration](/images/blog/probability-post-calibration.png)](/images/blog/probability-post-calibration.png)

_The above graphic displays a predictive [model report](/blog/faraday-model-reports) post-calibration. Model reports can be found in an outcome's analysis view._

So what does this mean? With probability scores, the groups of your prediction’s population–the deciles–are ranked in decreasing lift values, resulting in higher lift in your top attainers, or the people most likely to achieve the outcome.

With this update, Faraday’s predictions give you probability scores that are directly correlated to the probability of an individual achieving your outcome. If Jane Doe in your population has a 0.8 probability score, there’s an 80% chance that she will achieve the outcome.

Marketing campaigns have never been so predictable.

**[Create a free Faraday account](https://faraday.ai/signup) today.**

How model calibration helps Faraday improve customer prediction accuracy through probability scores.

Faraday probability scores: Improving prediction accuracy through model calibration

## What is market sizing?

Market sizing is a method of calculating a company’s revenue potential in a geographic market, which can provide crucial insights for competitive brands to be aware of when looking to expand, otherwise resources are likely to be wasted.

Market sizing is not a new concept, but more recent innovations in data collection and predictive analytics solutions have opened the door for more accurate market size calculations, enabling brands to make better go-to-market decisions and expand with more confidence and direction than before.

## Top down vs bottom up market sizing analysis

There are two methods of market sizing analysis: **top down**, and **bottom up**. In this article, we’ll look at both, and then explore how using predictive analytics for bottom up market sizing can provide you more accurate estimates while drastically expediting the analysis process, and give you actionable insight into where you’re most likely to have success penetrating.

### Top down market sizing

When using top down market sizing to calculate your market potential, you start at the highest level of the market that you’re in, where you find the largest possible size of the market you could acquire, then multiply it by the percent of the market that your product fits in.

For example, say you’re a brand that sells humidifiers, and you’re planning to launch a new humidifier that’s perfect for maintaining moisture levels in a newborn’s nursery. With the top down approach, your research shows you that the US market for humidifiers is \$700 million, and 65% of humidifiers sold annually are single-room, like your new product.

> **\$700m X 65% = \$455m**

Since, for the most part, the numbers that are relevant to your company and industry are likely already published elsewhere, this approach involves doing some research to find the populations and market values you need rather than calculating them yourself.

**Pros**:

- **It’s fast**. The research involved and the calculation are both straightforward and quick, so there’s not much time investment in a top-level market size estimate.
- **Accessible data**. Regardless of the outlet you want to source your data from, people have been publishing industry reports and analyses for years, so the data you need can easily be found via some time on Google.
- **Helpful at-a-glance**. Since top down market sizing looks at broad trends and market-wide data, it’s useful to be able to know, at a glance, if the space you’re looking to go-to-market in is worth the investment you’d have to make.

**Cons**:

- **It’s very broad**. As mentioned above, it’s useful to run a top down market size analysis for an initial glance at the market, but it’s unlikely to be specific enough for your company’s needs.

### Bottom up market sizing

Bottom up market sizing starts on the opposite end in that it begins with your niche. Using the same humidifier example, you’ll likely want to find people with children in the household to target since your new humidifier is for nurseries.

Through extensive research, data collection, and surveys, you find that there are 4 million people in this target group. To calculate the bottom up market size, you’d then multiply the number of people by the annual revenue you’d expect from them for the product–your customers are unlikely to buy more than one humidifier in a year, and its cost is \$100 per unit, so we’ll use \$100.

> **4 million people X \$100 = \$400m**

So what’s the verdict? Top down or bottom up market sizing? Since it uses data that’s relevant to your company, bottom up market sizing provides a more accurate estimate of your potential market–if your company has the bandwidth to put in the time. Fortunately, predictive analytics can help cut down that long timeline dramatically while providing you with geographies where your most likely buyers live.

**Pros**:

- **Backed by your data**. Since bottom up market sizing uses your own data & analytics through your customers, product, and cost data, results are much more tailored to your company, and they’re more realistic to boot.
- **As niche as you want it**. Rather than relying on industry-wide assumptions, this strategy begins and ends with your company’s niche.

**Cons**:

- **Time-intensive**. Performing the data collection required to accurately run a bottom up market sizing analysis is a long process in that, whether you’re conducting interviews or surveys, you’ll need to wait for results to come in.
- **Resource-intensive**. Assigning teams to create surveys, conduct interviews, act on their results, and so on can occupy a significant portion of their time.

## Calculating market size with predictive analytics

In the end, bottom up market sizing wins out as a more effective approach to calculate market potential. The downsides, of course, are the longer timeline and additional resources required to do it effectively.

This is where predictive analytics comes in–leveraging machine learning to predict individuals’ propensity to buy your products or services. With machine learning, your time-to-value in performing a bottom up market sizing analysis is dramatically reduced because it eliminates the need to design surveys and conduct interviews, conduct research, and wait for results.

Better yet, rather than spending extra time using your analysis to plan where you _think_ your campaigns will have the most impact, likely buyer scores show you _exactly_ where your high-intent buyers are at any geographic zoom that suits your needs.

### Traditional approach to bottom up market sizing

As we reviewed earlier, the typical traditional approach involves multiplying the number of people in the segment by the annual cost of your humidifier, which is simple enough math once you’ve done the required research to find the number of people in the segment.

At the end of the day, there’s still a lot of guesswork involved. In your research, you uncovered the raw number of potential buyers in your market, but the only direction you might have as for where to direct your campaign are surveys, which are unlikely to have reliable penetration for guidance, and assumptions–maybe the 5 driest states in the U.S. are the best bets to market your humidifier?

### Predictive approach to bottom up market sizing

With the predictive approach, you’ll take the segment you created above, then use AI to predict the propensity to buy for everyone in the segment based on real historical data. Machine learning algorithms surface patterns in the data to calculate just how likely each individual in this segment is to buy the product in likely buyer scores, and their forecasted spend over their lifetime as a customer of yours.

These likely buyer scores can be filtered by county, state, city, or metro, so that you have crystal clear indicators where your high-intent buyers are. You can even use your own points-of-interest, like brick and mortar locations, to perform radius-based likely buyer targeting for pin-point accuracy.

With Faraday, the predictive approach can be done in just a few clicks, saving you a significant amount of time and resources, providing more accurate results, and helping align your strategy through clear indicators for the locations you’ll have the highest likelihood of penetration in.

## How to do bottom up market sizing with Faraday

Using Faraday, the predictive approach for bottom up market sizing can be embedded wherever in your stack you need it in less than a day. No developers, no data scientists, and no long research timeline required.

### Connect data and define customers

To start, you plug in your data by mapping your data fields to Faraday properties.

![Image of Faraday dataset](/images/blog/market-sizing-dataset.png)

Then, in cohorts, you’ll utilize both your customer data and Faraday’s built-in consumer data to build the [exact cohort](https://faraday.ai/docs/cohorts/customers_from_hosted_csv)–or interesting group of people–you want. To continue with the nursery humidifier example, you’ll define a cohort for your customers, and a cohort using the trait for _children in household_, sourced from Faraday’s [rich, cookieless, opt-in consumer data](https://faraday.ai/features/data), to target with your propensity to buy predictions.

![Image of Faraday cohort](/images/blog/market-sizing-cohort.png)

### Predict propensity to buy to hone in on likely buyers

With your cohorts defined, build your predictive outcome by choosing your attainment, or your customers. Here, you’re defining your propensity to buy, or the likelihood that anyone in the U.S. is going to become a customer by making a purchase.

![Image of Faraday outcome](/images/blog/market-sizing-outcome.png)

Now that your predictions are defined, create a pipeline to make them actionable by choosing your **likely buyers outcome** and your **children in household** cohort.

![Image of Faraday pipeline](/images/blog/market-sizing-pipeline.png)

Machine learning algorithms then get to work predicting how likely people across the country with children in the household are to buy your new nursery humidifier. You can even further your bottom up market sizing analysis by generating customer personas and their predicted lifetime value with your brand.

### Deploy likely buyer scores to your analysis tools

Finally, deploy your likely buyer predictions back to your stack, via CSV file for versatility, or right back into your database or data warehouse for analysis in your BI tools. When deploying, filter to whatever aggregation level makes the most sense for your strategy: county, state, city, or metro. In this example, perhaps choosing state will reveal that the driest states in the country have the highest propensity to buy individuals.

![Image of Faraday pipeline](/images/blog/market-sizing-deployment.png)

With the predictive approach to bottom up market sizing, you have access to likely buyer scores anywhere in your stack in just a few clicks, providing insight into what geographic locations your company has the most high-intent buyers in so that your market size is more than just a rough estimate–it’s actionable and data-backed.

**Ready to try it out? [Create a free account](https://faraday.ai/signup).**

What is bottom up market sizing? What are its benefits? How can B2C brands accurately analyze markets without investing vast resources?

Bottom up market sizing: how to calculate market size using predictive analytics

**See our complete guide:** [Predictive AI for insurance brands](/blog/insurance-complete-context-guide).

---

If you’re a marketer in the finance industry, you know you have some heavy regulations to work with on [Google](https://support.google.com/adspolicy/answer/9917652?hl=en), [Facebook](https://www.facebook.com/business/help/2408667629202904), and other platforms, where consumer protections are put in place to help prevent discrimination. These regulations can make it difficult to reach your ideal customers when targeting new audiences, which likely means that you’re spending more than you need to on inefficient acquisition.

Complying with financial advertising regulations doesn’t mean you need to throw in the towel and accept worse performance. You can respect your customers’ privacy and be smart with your marketing strategy at the same time–you just need to think out of the box. That’s where built-in [third-party consumer data](https://faraday.ai/features/data) and [responsible AI](https://faraday.ai/features/responsible-ai) come in.

The data you have on your customers might be good, but purchases, adoptions, and clickstreams aren’t robust enough to give you a true leg up on your competitors, nor is it enough to ensure you’re not unknowingly discriminating against protected classes. Third-party data, when unified with your first-party customer data, can give you a 360º view of your customers, leads, and virtually any other group of people your business cares about.

With this breadth and depth of data in your pocket, you can then use AI to optimize your ad spend by surfacing your most likely-to-buy customers while remaining compliant by:

- Excluding protected classes from your predictions to ensure no unintended bias
- Targeting at the right aggregation level for your industry (counties, rather than zip codes, for example)
- Removing both human bias and error from the equation by using AI
- Monitoring and minimizing bias in predictive models through bias reporting

Faraday enables you to do all of these things–without a data science degree or programming knowledge–and in under 15 minutes. Here’s how.

## Connect your customer data to combine it with third-party attributes

To start, you plug in last quarter’s adoption data in by [mapping the data in Datasets](https://faraday.ai/docs/cohorts/customers_from_hosted_csv#option-a-each-row-represents-a-transaction-event).

![Image of identity set definition](/images/blog/finance-identity-set-definition.png)

Next, you use this new data to define a cohort–a group of people you’re interested in–of these new adopters.

![Image of cohort definition](/images/blog/finance-cohort-definition-booked-date.png)

## Build a predictive outcome to identify likely buyers

Now it’s time to predict which leads are most likely to convert. To do that, you’ll define an outcome using your _customers_ as your attainment cohort because that’s your end-goal–you want people to become customers and enter your _customers_ cohort.

Faraday makes this easy with step-by-step guides for [connecting to Google Ads](https://faraday.ai/docs/how-to/connections/google-ads) and setting up a [likelihood-to-convert prediction](https://faraday.ai/docs/how-to/predictions/likelihood-to-convert). Once your outcome is defined, Faraday will generate scores that tell you which individuals or locations are most likely to become customers.

![Image of new outcome screen](/images/blog/finance-new-outcome.png)

## Exclude protected classes with trait blocking

When describing your outcome, you choose _trait blocking_ to remove protected class traits. This ensures you’re not only complying with financial fair lending regulations, but are also using AI responsibly.

![Image of trait blocking checkbox](/images/blog/finance-trait-blocking.png)

## Choose the right aggregation level for your likely buyer predictions

Once your predictions are ready, set your aggregation level based on how high you’d like to zoom out of a location–such as by _county_ to remain compliant with Google’s restrictions on zip code targeting.

![Image of pipeline aggregation level](/images/blog/finance-pipeline-aggregation-level.png)

## Push high-scoring locations to your ad platform

With your highest-scoring locations in-hand, you plug them into your Google Ads campaign:

![Image of Google Ads campaign location upload](/images/blog/finance-google-ads-campaign-locations.png)

And your Facebook campaign:

![Image of Facebook campaign location upload](/images/blog/finance-facebook-campaign-locations.png)

That’s it! Your best-bet locations are plugged into Google and Facebook, and fewer than 15 minutes were spent making your predictions.

## Real results from a customer in the financial services space

A Faraday client in finance recently followed these exact steps to kick off a new acquisition campaign for an underperforming insurance plan, and they’re expecting a **3.2x lift in conversion rate** in the top 10% of individuals alone.

![Image of Faraday lift table](/images/blog/finance-lift-table.png)

Next up for them is adding direct mail into the mix, but the possibilities are endless.

[Sign up](https://faraday.ai/signup) free today.

In finance, remaining compliant to fair lending regulations doesn’t mean you need to accept worse acquisition performance. Learn how to use AI and third-party data to optimize ad spend by surfacing  your most likely-to-buy customers in under 15 minutes, while ensuring you're compliant to any relevant regulations.

How to optimize ad targeting and comply with financial advertising regulations

**See our complete guide:** [Powered by Faraday — embedding predictive AI in your platform](/blog/powered-by-faraday-complete-guide-embedded-predictive-ai).

---

Restaurants love Toast because it focuses on _their_ problems:

<a href="https://pos.toasttab.com/blog/il-primo-pizzeria" target="_blank"><img src="/images/blog/new-imperative-for-vertical-saas-built-in-ai/toast-pizzeria.png" width="372px" /></a>

Toast is a VSaaS (vertical software-as-a-service) - software **purpose built for unique industry workflows**. This means faster time to value compared to generic "horizontal" solutions. For example, Toast has a dedicated "Pizza POS" system with [easy topping swaps!](https://pos.toasttab.com/restaurant-pos/pizza-pos) A pizzeria wouldn't want to reinvent that wheel - but they also wouldn't want to pick a POS system that doesn't support it.

For the roofing industry, you _could_ customize Salesforce to track "Roof Area" - or you can use a [roofing CRM like Acculynx](https://acculynx.com/). There is a wonderful explosion of examples like this - companies that build exactly what their clients need, because they ONLY build for those clients:

- [bloomerang](https://bloomerang.co/) - for non-profits
- [mindbody](https://www.mindbodyonline.com/) - for wellness centers and spas
- [ALINE](https://alineops.com/) - for senior living
- [archy](https://www.archy.com/) - for dental offices
- and hundreds more.

With growth comes competition, and the question is: what's next for Vertical SaaS?

I would argue it is **incorporating AI features** that are specific to their industries. For VSaaS companies that haven't yet incorporated an AI feature, or are [looking to upgrade beyond first party data-powered features](/blog/why-first-party-data-and-rfm-is-not-enough), there are many options on the market. Here, we organize them into 3 levels - purpose-built, data warehouse-native, and low-level API. Each is useful for different use cases and organizations.

## Traditional focus on control points

Best-in-class VSaaS players have been focusing on [capturing "control points"](https://www.tidemarkcap.com/vskp-chapter/control-points-2-0). The control points are "back office" and "front office." Back office is the system of record, and VSaaS often starts by trying to become this - the "last system you turn off". Acculynx tracks roofing jobs and leads, while another Xero, an accounting VSaaS, [keeps the books](https://www.xero.com/us/security/data-protection/). From there, they can focus on integrating with or directly providing front-office technology - whatever the employee or customer interacts with. Every adult in the United States has probably held a [Toast POS](https://pos.toasttab.com/hardware/toast-go) in their hand.

## The new imperative - built-in AI features

What's next for VSaaS? How can you extend further into the value chain - or compete with an incumbent who has captured a control point? How can you [avoid ChatGPT-based extinction](https://www.tidemarkcap.com/post/ai-extinction-or-evolution)? One possibility is adding AI features specifically tuned for an industry, which only VSaaS can provide.

There are at least 2 reasons VSaaS is well positioned for AI.

- **Data**. As a system of record, a VSaaS might be the _only_ place a business can get the data it needs to make a critical decision or prediction.
- **Semantic layer**. Since VSaaS understands the semantics of its vertical - in other words, it knows what pizza toppings or roof sizes _mean_ - it can automatically build and use AI models.

As [Tidemark](https://www.tidemarkcap.com) puts it, **"flip your product from being reactive to proactive."** For example, Acculynx rates every roof lead 🟢 🟡 🔴 and [doubled conversion rates for clients who focused on green-light leads](https://www.prweb.com/releases/2023/4/prweb19276673.htm).

## Taking the first step

Assuming building AI into their product is critical path, VSaaS vendors must decide where to start. It can be helpful to think of the options as organized into levels from most out-of-the-box to lowest level. Different VSaaS companies will find different levels to be the most appropriate.

![](/images/blog/new-imperative-for-vertical-saas-built-in-ai/level-advantages.png)

### Level 2 - easiest - purpose built AI

The most accessible way for VSaaS to incorporate AI into its products is to adopt an existing lower-level component whose unit of prediction is the same - one that is purpose built for predicting against people, products, or search. For example, any system that deals with people can build predictions about their behavior by using Faraday's [business outcomes](https://faraday.ai/docs/product/outcomes). A system in charge of inventory can add intuitive AI-based search by incorporating Bloomreach's [product search](https://documentation.bloomreach.com/discovery/reference/product-search-category-api). Systems for managing creative assets can build next generation functionality by incorporating AI features like Cloudinary's [automated image editing and generative background replacement](https://cloudinary.com/products/cloudinary_ai).

### Level 1 - data warehouse native

Going a level down, VSaaS looking to develop its own AI capacity outside of what's already on the market in level 2 should evaluate the machine learning components [built into data warehouses](https://cloud.google.com/bigquery/docs/bqml-introduction). These are not just for one-off analyses; entire applications can be developed on top of them. This level sits at the sweet spot between specific units of prediction in level 2 and raw HTTP APIs in level 0. Generally controlled by SQL commands, they treat structured, unstructured, and even [file/object data](https://cloud.google.com/bigquery/docs/annotate-image) as tables and allow feature engineering, modeling, evaluation, and prediction as SQL queries. They are designed to process data at any scale, automatically shuffling data and managing memory without requiring manual partitioning or configuration by users. So, if you build a solution on top of them, you get scaling essentially built in.

Almost all data warehouses now allow you to do [generative AI](https://faraday.ai/blog/quickstart-use-bard-in-bigquery). This is much more attractive for batch use cases than creating error-prone HTTP connections to LLM APIs across many rows of data (you wouldn't use this for building chatbots that require low latency - see level 0). Don't forget about predictive use cases too - [time series modeling](https://towardsdatascience.com/time-series-forecasting-in-snowflake-using-sql-6ce7cedce862), for example, is available on all of the major data warehouses and allows sophisticated projections with built-in and custom holidays. [SQL-based classification and regression](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-boosted-tree) using XGBOOST and random forest are bread-and-butter use cases that fit perfectly with tabular input and output data; once you've done feature engineering with standard SQL functions, it's hard to imagine a simpler way. [Unsupervised clustering](https://docs.aws.amazon.com/redshift/latest/dg/tutorial_k-means_clustering.html) is also available.

### Level 0 - raw API

A very rich set of services, from Google's [Vertex AI](https://cloud.google.com/vertex-ai) to [OpenAI's Enterprise-friendly models](https://openai.com/enterprise), exist as HTTP APIs. This is the lowest common denominator and is accessible from all systems. It is also particularly appropriate for just-in-time calculations such as generative prompts used by chatbots or online fraud predictions using random forest models mounted alongside [feature stores](https://cloud.google.com/vertex-ai/docs/featurestore) for instant response. When planning an AI feature for a VSaaS, it might seem necessary to master an entirely new API. However, low-level systems are often better suited for specific real-time use cases, while asynchronous or batch workflows should first explore the potential of level 2 or level 1 solutions.

## Choosing a level

A few questions can suggest where to start:

- Is there already an out-of-the-box prediction infrastructure for your use case? Companies should always evaluate level 2 purpose-built solutions before committing to building low-level systems.
- What is the time between a prediction being created and its use? For example, if you're incorporating search, people expect results immediately; using an existing level 2 vendor may be the fastest approach. However, if no solution aligns with your industry needs, you may need to skip Level 1 and develop a [level 0 solution](https://cloud.google.com/vertex-ai/docs/predictions/get-predictions). Conversely, if you plan to rank a lot of records in asynchronous batch use cases, a level 1 solution is likely sufficient.
- Is there industry data that can extend a client's own data? For example, fraud detection vendors incorporate geographic fraud data in their scores. Faraday has a [national dataset of all US consumers](https://faraday.ai/features/data) that automatically enriches predictions made on its platform.
- What kind of scrutiny will your AI receive? For example, if you are making predictions about people, consider how you will implement [Responsible AI](https://www.brookings.edu/events/what-is-responsible-ai/). Some level 2 vendors [automatically build in reportable controls and metrics](https://faraday.ai/features/responsible-ai); some level 0 vendors [let you build your own](https://www.datarobot.com/blog/bias-mitigation-with-datarobot/).

## The imperative

If you were starting a VSaaS product from scratch, what would be your wedge? Some form of AI is a good guess. And if you are a VSaaS incumbent, how do you defend your position? You have an advantage in the data and semantic layer you already hold. A thoughtful approach to AI infrastructure options can boost your efforts and minimize your time to value.

Vertical SaaS (VSaaS) is software built exactly for a particular industry. The next generation of VSaaS is incorporating exactly the AI that people need.

All posts