[Burrow](https://burrow.com) is an innovative furniture brand founded in 2016\. From starting out with thoughtfully designed modular couches to recently expanding their offerings to shelving, coffee tables, and even rugs, they have continuously pushed to understand their customers and cater to their needs.

## The goal

Burrow wanted to personalize its customer journey to drive better conversion rates and more purchases as they expanded their product lines.

## The challenge

Like most companies, Burrow had a cold start problem: they knew a lot about their current customers, but very little about brand new customers or potential customers who had signed up for their newsletter.

## Faraday \+ Iterable

Enter Faraday \+ Iterable. With [Faraday’s Identity Graph](https://faraday.ai/features/faraday-identity-graph), the Burrow team suddenly had access to 1,500+ data points on almost every adult in the US they could combine with their contact data. And with Faraday’s AI tools, the team could identify the patterns and trends of their customers to build segments of leads who looked just like them.

All of these insights then [flow directly to Iterable](http://faraday.ai/docs/integrations/iterable), where their automated journeys enable customer engagement across multiple channels with minimal manual effort. By leveraging automation, informed by Faraday, Burrow delivers timely, relevant content that enhances the customer experience while saving time and resources.

## The results

By partnering with Faraday, Burrow was not only able to know what all of their leads looked like, but which looked like customers who had taken specific actions in the past—whether it was to purchase from a specific category, spend a certain dollar amount, or even prefer a specific color couch over another.

In this way, the Burrow team could engage leads who previously only had provided an email address and deliver highly tailored messaging that matched their consumer profile, with suggested products based on what they were most likely to care about.

All of this messaging was delivered with Iterable, which ensured it was delivered at the right time, and by the right channel for an optimal engagement experience.

With Faraday \+ Iterable, Burrow is building a [predictive customer experience](https://faraday.ai/blog/predictive-customer-experience-is-the-future) that makes it enjoyable for everyone to shop—whether you’re a repeat customer or simply signed up on the newsletter.

Burrow used data and machine learning to power personalization and drive higher conversion rates.

How Burrow uses customer predictions to drive intelligent growth

At Faraday, we’re on a mission to help [businesses of all kinds](https://faraday.ai/stories) predict customer behavior. Whether you’re a [credit union](https://faraday.ai/stories/advia-credit-union) that wants to predict the next best offer for your current customers, a [construction brand](https://faraday.ai/stories/window-manufacturer) looking to increase lead conversion rates, a [sales platform](https://faraday.ai/stories/salesrabbit) set on enhancing your product with customer predictions to increase rep efficiency–or anything in between–we’ve got you covered.

While we’ve taken great leaps in the 10+ years since our founding to make this type of data science more accessible to non-data-scientists, we know that it can still be a struggle to interpret what exactly you should pay attention to within your outcomes and recommenders so that you can use your customer predictions with maximum effectiveness.

To this end, let’s take a quick look at an example of the output of an outcome and highlight the exact pieces of info you can focus on so that you can understand how to activate on your predictions. For recommenders, check out our [accompanying blog post](/blog/how-to-interpret-recommenders).

## Using the lift table

When you’re viewing an [outcome](https://faraday.ai/docs/abstractions/outcomes), the **lift table** is one of the analysis options available to you, and a great place to start.

Every outcome has an _average conversion rate_ — this is the portion of every eligible person that attained the outcome. Given a lead conversion outcome, for example, the average conversion rate is just the average lead conversion rate you’ve experienced to date.

In the lift table, you’ll find performance broken down by probability range into 10 groups, or _deciles_. The table sheds light on how likely people in each decile are to attain the outcome, including in comparison to that average attainment rate. The comparison of a given decile’s attainment rate to the average attainment rate is called **lift**, which you can see in the rightmost column. The higher the lift, the better the performance.

[![Faraday outcome's lift table with decile and lift highlighted](/images/blog/product/lift-table.png)](/images/blog/product/lift-table.png)

As you review the table, the columns you’ll want to keep an eye on are **decile** and **lift**. You can look at the lift on a scale around the value 1.0, which represents no change against your average conversion rate. When the lift moves positively away from 1.0, that means you’re in a decile that will do better than normal, while moving below 1.0 indicates the opposite.

To illustrate, look at the top decile — this contains the 10% of all people who scored highest. Faraday expects that out of everybody who receives a score this high, about 95% of them (the **precision**) will attain the outcome. This is way higher than normal for this outcome — in fact, about 90% higher (1.896x lift).

## Choosing a cutoff

If you only pursue this top decile, you’ll have a great success rate, but you’d be leaving a lot of other potential attainers behind. When predicting customer behavior like this, an important job for a human is to decide where the cutoff point (“threshold”) should be.

In general, you can use this scale to determine which people in your pipeline’s eligible population you should focus more on, and which you should focus less on. In the above table, you can see a positive lift all the way to the top 50% of scorers.

When you create a [deployment](https://faraday.ai/docs/abstractions/deployments) for your predictions, you can match this by applying a filter on the outcome’s probability percentile at “\> 50,” ensuring you’re focusing on places where you’re likely to see positive lift.

Advanced users can leverage probability values, along with profitability, to determine a cutoff based on expected value (EV).

A short guide on how to interpret your predictive outcomes in Faraday.

How to interpret outcomes in Faraday

At Faraday, we’re on a mission to help [businesses of all kinds](https://faraday.ai/stories) predict customer behavior. Whether you’re a [credit union](https://faraday.ai/stories/advia-credit-union) that wants to predict the next best offer for your current customers, a [construction brand](https://faraday.ai/stories/window-manufacturer) looking to increase lead conversion rates, a [sales platform](https://faraday.ai/stories/salesrabbit) set on enhancing your product with customer predictions to increase rep efficiency–or anything in between–we’ve got you covered.

While we’ve taken great leaps in the 10+ years since our founding to make this type of data science more accessible to non-data-scientists, we know that it can still be a struggle to interpret what exactly you should pay attention to within your outcomes and recommenders so that you can use your customer predictions with maximum effectiveness.

To this end, let’s take a quick look at an example of the output of a recommender and highlight the exact pieces of info you can focus on so that you can understand how to activate on your predictions. For outcomes, check out our [accompanying blog post](/blog/how-to-interpret-outcomes).

## Understanding AROOP

A [recommender](https://faraday.ai/docs/abstractions/recommenders)’s _metrics_ tab will show you the average rank of observed property (AROOP), which represents the average ranking of the true next event during training. In other words, the average number of recommendations it took to recommend the correct actual behavior.

What’s an observed property? Many brands use a Faraday recommender to identify the so-called “next best offer.” In this scenario, the event would be “transaction” and the property would be “product.” A recommender’s job is to predict which _product_ property will occur in the person’s next _transaction_.

Let’s look at an example for a fruit seller. In the below table, John’s actual behavior landed in one of the “top 2” recommendations from Faraday, while Jane’s was in the top 1\! The overall AROOP for the recommender would be the average of these ranks: **(<span style="color:red">2</span> \+ <span style="color:green">1</span>) / 2 \= 1.5**.

<table>
  <thead>
    <tr>
      <th>Name</th>
      <th>Recommendations</th>
      <th>Observed property</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td>John</td>
      <td>
        <ol>
          <li>
            Apple
          </li>
          <li>
            <strong><span style="color:red">Orange</strong></span>
          </li>
          <li>
            Kiwi
          </li>
          <li>
            ...
          </li>
        </ol>
      </td>
      <td><strong><span style="color:red">Orange</strong></span></td>
    </tr>
    <tr>
      <td>Jane</td>
      <td>
        <ol>
          <li>
            <strong><span style="color:green">Kiwi</strong></span>
          </li>
          <li>
            Apple
          </li>
          <li>
            Orange
          </li>
          <li>
            ...
          </li>
        </ol>
      </td>
      <td><strong><span style="color:green">Kiwi</strong></span></td>
    </tr>
  </tbody>
</table>

## Using the accuracy table

Looking at a recommender’s **accuracy table**, accuracy refers to how often the observed property is contained in the “top X” recommendations.

For example, if the accuracy for a threshold of 3 is 0.56, then this Faraday recommender correctly predicts the observed property to be in the top 3 recommendations 56% of the time.

[![Faraday recommender's accuracy table](/images/blog/product/accuracy-table.png)](/images/blog/product/accuracy-table.png)

Depending on your use case and the medium you’re using recommendations in, you can use accuracy up to the appropriate threshold that makes sense for that medium. Choosing the threshold is the equivalent of finding the balance between the accuracy of the recommendation and overwhelming information. If you recommend _everything_ to the customer, you’re guaranteed that their next action will be one of your recommendations, but that’s not very helpful\!

If you want to take a deeper look at how each trait (feature) impacted your predictive models, check out our blog on understanding [model reports](https://faraday.ai/blog/faraday-model-reports).

A short guide on how to interpret your predictive recommenders in Faraday.

How to interpret recommenders in Faraday

Let's take a look at some of the latest features in Faraday.

## Event stream analysis

[Events](https://faraday.ai/docs/abstractions/events) are the most critical pieces of data used in Faraday–they help define nearly everything you do, after all. When an event stream that you’ve created stops receiving data for one reason or another, it could be frustrating to discover that you’ve been working with data that is no longer up-to-date.

To help alleviate this frustration, we’ve updated the events index view to display the number of events being used in each event stream, when the most recent event was added, and the status of the event stream. Additionally, each event stream now includes an analysis view that indicates these same event counts.

[![Screenshot of event stream analysis in Faraday](/images/blog/product/event-stream-analysis.png)](/images/blog/product/event-stream-analysis.png)

Overall, this change should help you stay on top of your data flow into Faraday and ensure that your predictions are always up-to-date using your latest events.

## Enrichment precision filtering

In identified and referenced [deployments](https://faraday.ai/docs/abstractions/deployments), an enrichment precision column is included for each trait provider your account is subscribed to. Enrichment precision tells you how well Faraday was able to assign traits to identity information you provided, and is broken down into two levels: person and residence.

- Person enrichment precision means that Faraday is able to assign person-level traits to an identity, like age, consumer habits, or marital status.
- Residence enrichment precision means that Faraday is able to assign address- or property-level traits to an identity, like home value or number of bedrooms.
- Region (postcode) enrichment precision means that Faraday is able to assign region-level traits to an identity, like average commute time or average property tax.

## Lookup API support for identity sets

For our [Lookup API](https://faraday.ai/docs/features/lookup-api) users, you’re now able to use multiple identifiers in a single identity_sets array to find a match for a person. If the root-level identifier does not find a match, Faraday will use each included identifier until a match is found.

[![Screenshot of identity sets used in an API request](/images/blog/product/lookup-identity-sets.png)](/images/blog/product/lookup-identity-sets.png)

With this update, your Lookup API workflow should be simpler and more streamlined when it comes to finding individuals in the Faraday Identity Graph.

---

Check out our [changelog](/changelog) for a dated list of updates.

Explore the latest Faraday updates, including tracking of event stream change over time and filtering based on Faraday enrichment type.

What's new: event stream analysis, enrichment precision filtering & more

It’s no secret that [third-party data](https://faraday.ai/blog/first-party-vs-third-party-data-marketing) is one of the most critical components of effective, data-driven AI/ML projects. It adds additional layers of depth and complexity to predictive models to help them perform better, provides rich insight into who your customers and leads are outside of their engagement with your business, and more.

In Faraday, responsibly sourced third-party data is [built in](https://faraday.ai/features/faraday-identity-graph), and we recently pushed our biggest-ever update to the Faraday Identity Graph (FIG). 827 brand new traits alongside fresh updates to hundreds of existing FIG traits means that your customer predictions are now even more powerful–without any action required on your end, as Faraday automatically considers these new traits when building models for you.

From lifestyle [traits](https://faraday.ai/docs/abstractions/traits) like `Environmentally focused household` to financial segments like `Affluents`, Faraday’s algorithms have even more lenses through which your customer data can be analyzed, resulting in even more powerful predictions.

For example, a financial institution might find that a prominent feature in their [outcome](https://faraday.ai/docs/abstractions/outcomes) is another new trait, `Likely to use an investment broker`, which could indicate that they should leverage their brokerage service more heavily. They could append this trait to their pipeline that includes a likelihood to convert outcome so that, maybe instead of sending an email to people for whom this trait is true, they reach out directly via phone to talk about investment services.

Similarly, a business looking to focus their ad spend might use `Instagram user` to find their leads that are most likely to be active on Instagram. With this knowledge, they can then target their ads specifically on Instagram as opposed to using a widespread approach to see what sticks.

Predicting customer behavior is nothing without a strong foundation of first and third-party data. Faraday’s data is regularly refreshed with both updated and new traits so that your predictions are as accurate as possible. If you’re interested in learning more about these new traits, contact [support](https://support.faraday.ai) or your account manager.

The Faraday Identity Graph recently received its biggest-ever update, with over 800 brand new traits and updates to hundreds of existing traits.

1,000+ new and updated traits now live in Faraday

At Faraday, we automatically detect and correct for geographic bias in our training data through a process we call “geonormalization”.

## Why geonormalize?

It's easiest to explain through some examples, so let's walk through two.

**Example 1: to re-balance an unbalanced training population**

Say you have a business with two customer bases: California and Nebraska. The business started in California, so its customer base in California is 10x what it is in Nebraska. Without geornormalization, because the business has more customers in California and those customers look totally different to those in Nebraska (e.g. higher household income in California), everyone in California is scored higher than those in Nebraska.

**Example 2: to allow for a prediction to generalize over geographical areas not covered in the training data**

If your business started in New York, so all of your data–demographics, financials, and so on–is New York-based, and now you're trying to find _brand new_ business in California, the predictive model won't have been able to learn about what makes California unique in terms of that data, so the model will struggle to learn and its predictions will be unreliable.

Neither scenario is particularly helpful for growth!

Geonormalization adjusts both of these types of geographic bias with geography-based scaling instead of a raw value: Jane Doe is in the top 10% of scores in her state instead of the top 10% of scores for everyone.

Without geonormalization, you might define someone as "wealthy" if their net worth is $500k. Having a definition this static can present problems when comparing people from different demographic and financial backgrounds. With geonormalization, and keeping the above examples in mind, the definition of wealthy becomes more dynamic: "they have a net worth over twice as much as the average in their county."

Just because someone lives in a location that’s different from your customer data doesn’t necessarily mean that they should score lower than everyone that resembles your customer data.

## How does Faraday geonormalize?

Hence the need for a correction factor, to ensure that we are able to find the most likely customers in all of the regions our client wants to expand into. Our approach requires a detection algorithm and a correction algorithm

### Detection

We use a simple, but effective, algorithm. We compare the market penetration (customers / total possible customers) among each distinct geographic area at the desired level of analysis. If the largest market penetration is greater than 100x the smallest market penetration then we perform our correction algorithm during training.

For detections we start at the largest geographic area of interest, the state level, and work our way down to the smallest geographic area of interest, the postcode level. If at any point during the detection, the 100x threshold is met we perform the correction for that geographic level. Therefore, we are always applying the correction at the largest level possible.

### Correction

We use a two-pronged approach to correction: instance weighting for the training examples, and bias correction for the training features.

#### Instance weighting

We assign a weight to the positive examples calculated from the penetration rate of those positive examples in their respective geographic area. This in essence levels the playing field and gives a boost to the positive examples from areas where there are relatively fewer examples (unsaturated markets) and gives a penalty to the positive examples from saturated markets.

From a modeling perspective, we are tricking the model to believe that the good examples are just as likely to exist in any of the geographic segments. This leads to less bias amongst the features used to distinguish good examples from bad examples.

#### Feature correction

Our other method we employ in tandem with the instance weighting, is to transform features so that we level the playing field across the geographic segments. Instead of providing the model with raw features, we transform them so each person is represented by the percentile they occupy within their segment. Again, this one is probably easiest to explain via an example.

Instead of providing raw household income values of \$84k for CA resident A and \$66k for NV resident B, we provide the model with how they rank amongst their peers within their respective states. I’ve chosen the median income for each state, so the model would receive 50 for resident A and 50 for resident B.

By correcting the features, we provide the model with fewer discriminatory features with which to determine that everyone from the more saturated geographic segment is a better fit than everyone from the less saturated segments.

## Conclusion

Geographic bias correction, aka “geonormalization”, means that when using Faraday to expand your business into new markets, you can do so confidently knowing that our models will not just default to recommending people from markets in which you already have a significant presence. Grow your business confidently with predictions from Faraday.

At Faraday, we automatically detect and correct for geographic bias in our training data through a process we call “geonormalization”.

Geonormalization in Faraday

Predictive patterns change over time. When it comes to predicting customer behavior, it’s entirely likely that a person who’s been a lead for say, three months, is going to behave differently than someone who just signed up for your mailing list. The former has been receiving your email drip for a few weeks, is aware of your offerings, and probably has a decent idea of what they’re looking for. The latter is much closer to the top of the funnel, and is just getting to know your business better.

Why does this matter? Well, the person that just subscribed to your mailer might be less likely to convert compared to someone who’s been interacting with your business for 3 months - or they might not be! If the behavior “visited your site 3x” tends to be highly predictive of conversion, that’s only relevant to leads who’ve had the time in the funnel to actually visit your site more than once, so a different model should be used for fresh leads. Additionally, aggregated data is used to capture the situation of a person at the time of prediction. For example, has a new email been sent since we last produced a prediction?

With dynamic prediction, we create predictive models for several tenure bins, or periods of time, that someone has been in the eligibility cohort that you’re using for your prediction (i.e. their funnel stage). Then, we use the best possible model to make predictions on an individual based on that tenure bin. In the below example, you can see two strategies applied (A and B) across four tenure bins (0, 10, 20, and 30 days). In it, strategy A scored higher for the bins of 10 and 20 days, while B scored higher for 0 and 30 days, which means the optimal scoring combination is to use strategy A to score people that have been in the cohort for 0-10 days, strategy B for those in it for 11-20 days and 21-30 days, and A again for those in it for 30+ days.

[![Graphic of dynamic prediction tenure scoring](/images/blog/dynamic-prediction/dynamic-prediction-1.png)](/images/blog/dynamic-prediction/dynamic-prediction-1.png)

To illustrate this point further, below is an example of a pipeline that uses tenure bins to select the best model for each tenure group. In it, you can see the **pipeline population** group is broken down into three tenure bins, each of which has a “best” predictive model that’s used for scoring.

[![Graphic of dynamic prediction pipeline](/images/blog/dynamic-prediction/dynamic-prediction-2.png)](/images/blog/dynamic-prediction/dynamic-prediction-2.png)
_For further reading on Faraday model calibration and probability scores, check out [this blog post](/blog/faraday-probability-scores)._

In short, dynamic prediction enables us to provide scores that update with your data, ensuring accurate, powerful predictions for all stages of the customer lifecycle.

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

Predictive patterns change over time. Faraday uses dynamic predictions to choose the best model for you based on subject tenure.

How Faraday uses dynamic predictions to choose the best model for you

## What is identity resolution?

Identity resolution is the process of taking all of the files and databases of people data in your organization and figuring out "who is who" so that you can unify individual records into a single entity. For example, one database might have email, and another database might have street address; how do you connect them? Identity resolution is the answer.

Within identity resolution, there are two broad categories: **known identity** and **anonymous** (unknown) **identity**. Known identity is figuring out the email, phone number, and/or street address of someone. If you have known identity, you can find someone in the real world. Anonymous identity is defining some IP address, device ID, browser fingerprint, or cookie that represents a person without actually knowing who they are in the real world. In either case, you’re trying to get a join key or universal ID that lets you combine data from different sources across time.

How does identity resolution work? In a few different ways:

- You _explicitly_ collect known identifiers like email in web forms or addresses in orders/transactions.
- You _implicitly_ collect anonymous identifiers like IP addresses, cookies, as they browse.
- You stitch together known and anonymous identifiers when people click links in emails, log in, enter billing and shipping data, etc.
- You connect known identifiers with marketing data like age, gender, and household income using third parties like Faraday.
- You de-duplicate and "master" records: e.g. by saying that two different emails belong to the same person
- You upload unknown identifiers to ad networks and they resolve them into users on their platforms.

Finally, it's important to know the terms first- and third-party data. **First-party data** is data that you collect and own, and can include both known and anonymous identifiers. It also includes transaction amounts, order details, product details, etc. **Third-party data**, on the other hand, is data that is owned by others, but is available for specific uses. (You may also hear about “zero-party data,” which is a special kind of first-party data that users explicitly provide, such as by filling out surveys.)

When you unify first and third party data, you can get age, gender, household income, and other traits for a user so that you know both what they bought (first-party data) and who they are (third-party data). You’ll generally get the highest enrichment or match rate by starting with known identity, but it's possible to start with anonymous identity, too.

## Why does identity resolution matter?

If your business has more than just one useful database of information (which is highly likely), identity resolution is mandatory in order to properly understand not only who’s who within your data, but also how they’re engaging with your business. Doing so opens up a world of use cases that can be done efficiently because you’re able to group similar customers and leads together: [personalize their journeys](https://faraday.ai/templates/thematic-personalization), recommend first-and-[next best offer](https://faraday.ai/templates/next-best-offer), plan [retention campaigns](https://faraday.ai/templates/churn-scoring), and more.

For example, transaction data stored in back office systems can be combined with behavior observations in the marketing or product teams, with call logs from customer-facing teams, and so on. To illustrate this latter point, customer [churn prediction](https://faraday.ai/blog/churn-prevention-machine-learning) is often much stronger when it takes into account activity like messaging or calling.

Taking this a step further–when generative AI is available–identity resolution can help take unstructured data from call center transcriptions and combine it with structured data like transaction histories. This allows you to use sentiment analysis or entity extraction to create data attributes (i.e. predictive features) that can be combined with other first and third party features in predictive models, such as [lead scoring](https://faraday.ai/solutions/lead-management).

## Why identity resolution is difficult to implement

Identity resolution is important, but it's hard to implement. To start, the datasets involved need to have PII that can be compared. For example, maybe you have transactions with billing addresses included in one dataset, and views/clicks by email address in another. To resolve the identities in these two datasets, you’d need to purchase third-party email hashes connected to postal addresses so that both have billing address and email data, _then_ you’d need to ensure the data is standardized so that they can be compared.

The process is further complicated when you consider that people aren’t static–they move addresses, they have kids, their habits change–life goes on. You'll need to rent or purchase historical address data to make your graph complete. Your customers and leads change, and your data should be able to change with them.

## What does the identity resolution market look like?

There are a wide variety of identity resolution products on the market. Some are pre-integrated into the systems that use them, such as traditional "packaged" CDPs, purpose-built person-level AI infrastructure like Faraday, and others. These identity resolution systems primarily serve the purpose of the software they're integrated with, and offer the fastest time-to-value. Software in the master data management space like Reltio is dedicated to resolving and de-duping records for use by downstream systems.

There are also data warehouse-native identity resolution packages, such as Hightouch Identity Resolution or AWS Entity Resolution that run directly inside of a customer's cloud account or data warehouse. These provide standard functions for resolving identity that can be applied to any business, though they won't be immediately usable out of the box. TransUnion and other traditional data aggregators offer identity resolution packages on the Snowflake Marketplace that serve to connect first-party data to third-party identifiers and data. Finally, consultants like Deloitte will often build custom identity resolution projects on a per-client basis, if that client has previously purchased third-party data.

Due to competitive pressure from all of the data warehouse-native and standalone identity resolution providers, some software with built-in identity resolution like Faraday now allow data warehouse-native identity resolution too, which can be a good option that combines the low time-to-value with a flexible, proven base for other software and processes to be developed on top of.

## How Faraday’s identity resolution works

Faraday’s advanced identity resolution is built in, which means you don’t need to separately license any data or go through the laborious process of manually unifying it with your own to create distinct profiles of your customers and leads. All parts are included: from data and data unification that’s continuously up-to-date and responsibly sourced, to identity resolution and AI-powered customer predictions. Whether you’re interested in prioritizing your best leads and rejecting leads that won’t end up converting, seeing which customers are going to churn or finding their next best offer, Faraday has you covered from end to end.

To start, Faraday securely ingests your data through a [connection](https://faraday.ai/docs/abstractions/connections) to wherever your data is stored (or via CSV file), after which you describe your data to Faraday via [datasets](https://faraday.ai/docs/abstractions/datasets). In your datasets, you’ll tell Faraday what personally identifying information (PII) fields to look for (column mapping), as well as what [events](https://faraday.ai/docs/abstractions/events) take place in your data, which you’ll use to define your customer prediction objectives. Everything Faraday does is [fully API-enabled](https://faraday.ai/docs/reference), too.

With your data defined, we search the Faraday Identity Graph (FIG) for matching PII through fields like `email`, `first_name`, and `address`. Once a match is found, all data that you have on this individual is unified with and enriched by their data in FIG. From demographics, to financials, property data, and more, 1,500+ robust traits supplement your data on how they interact with your business with how they exist _outside_ of those interactions.

[![Graphic of Faraday identity resolution](/images/blog/identity-resolution/identity-resolution.png)](/images/blog/identity-resolution/identity-resolution.png)

The result is a unified, enriched customer profile that’s embedded directly into your applications and workflows–with customer predictions on top–for all of your customers and leads, ensuring that your teams have all of the information they need to engage effectively.

At the end of the day, identity resolution is critical to unlocking truly data-driven marketing and AI/ML projects. With it, all of your data comes together from its disparate sources to form unique identities for each individual. These identifiers cover their engagement with your business through visits, email addresses, transactions, etc, their marketing highlights like age and income, and any other traits that you have. With identity resolution, you can effectively predict which leads are most likely to convert and which you shouldn’t waste time and money on, which customers are most likely to churn, their buyer persona, what product or service to recommend next, and more.

Faraday handles the ML struggle so that you can focus on your downstream applications and workflows.

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

Faraday unifies your data with rich third-party data and applies advanced identity resolution techniques to reveal panoramic views of your customers and leads.

How Faraday unifies your data with the Faraday Identity Graph for advanced identity resolution

AI is everywhere. Businesses of all kinds are using it for every use case imaginable. From creating copy for their emails or website, to generating graphics for their blog, to [predicting customer behavior](https://faraday.ai/features/customer-behavior-predictions) and beyond. While using AI for the more innocuous cases like brainstorming ideas or generating art tends to leave you with the set-it-and-forget-it mentality, that’s not the case in the realm of predicting customer behavior. Here, [explainable AI](https://faraday.ai/blog/what-is-explainable-ai-why-is-it-important) is critical in helping non-data scientists understand what data your predictive models used to come to their conclusions, and whether or not you can trust them.

[![Graphic of dynamic prediction tenure scoring](/images/blog/transparent-reporting/transparent-reporting.png)](/images/blog/transparent-reporting/transparent-reporting.png)

For this reason, every model in Faraday comes with at-a-glance performance reporting so that you can quickly assess how strong your predictive model is. Beyond this, you can dig into things like [feature importances and directionality](https://faraday.ai/blog/faraday-model-reports) to see what individual features from the Faraday Identity Graph and [your own data](/blog/first-party-features) had the greatest impact in creating the predictive model, and even where specifically within those features they had such impact. Additionally, reporting on ROC and lift are included.

On top of this at-a-glance reporting, each model comes with a complete, in-depth technical report that digs into the nitty-gritty that data scientists love \- from analysis of training data to model calibration, cross-validation, and more. Further, Faraday strongly believes in [Responsible AI](https://faraday.ai/features/ai-safety-and-responsible-ai), which means that this technical report also includes [score explainability](https://faraday.ai/blog/faraday-score-explainability) and background on how Faraday came to the conclusion of its bias and fairness assessments.

Don’t _just trust us_ (or any other AI that you use\!) \- our reports speak for themselves.

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

From at-a-glance performance reporting to feature importances with directionality to in-depth technical reporting, Faraday helps you understand the models we build.

Transparent predictive model reporting with Faraday

## What is a feature in machine learning?

In machine learning, a feature is a piece of data that’s used to train a predictive model. A feature can come in a variety of different formats, be it a static trait like age, whether or not someone’s a frequent home remodeler, or some value that’s related to the events taking place in your own data.

Once these features have been fed into the machine learning algorithms, predictive models begin learning from the data by looking for patterns to analyze, and the end result is predictions that help your business find your most likely-to-convert leads–and reject the least likely-to-convert ones–find more high-LTV customers, and more.

## Creating first-party features from your data

Once your customer and lead data is ingested through a [connection](https://faraday.ai/docs/abstractions/connections) to your data warehouse or a CSV upload, you’ll point Faraday toward the [events](https://faraday.ai/docs/abstractions/events) and [traits](https://faraday.ai/docs/abstractions/traits) within your data. While doing so, you’ll define when an event took place, its value, and any relevant event properties (e.g. the acquisition channel of the event).

[![Screenshot of an event stream's configuration in Faraday](/images/blog/first-party-features/event-features.png)](/images/blog/first-party-features/event-features.png)

Then, when you’re creating a prediction in Faraday, we’ll use these properties that you define to engineer features to be used alongside the [Faraday Identity Graph’s 1500+ vivid traits](https://faraday.ai/features/faraday-identity-graph). While analyzing the predictions you’ve created–like the likely-to-buy-again outcome below–you’ll find your first-party features with a sparkle next to them.

[![Screenshot of an outcome's feature importance in Faraday](/images/blog/first-party-features/outcome-features.png)](/images/blog/first-party-features/outcome-features.png)

In the above example, a first-party feature was created based on the date the last subscription box was purchased by a customer of this client’s in `last_box_purchased`, and another for the category of that box from an event property in `orders category` (orders being the event stream, category the event property defined within the stream). Lastly, a feature was created for the `first_box_assigned` trait–designating which category of subscription box the customer received on signup (kitchen, camping, etc).

These three features had a major impact on the scores of people in this outcome, and were highly predictive of the behavior the client was predicting for: likelihood of buying again.

You can read more about how individual features impact an outcome’s predictions in the data section of our [outcomes](https://faraday.ai/docs/abstractions/outcomes) docs.

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

Faraday automatically engineers machine learning features based on your first-party data to be used as predictors.

All posts