This spring, a team of interns from [Middlebury College](https://www.middlebury.edu/#) joined Faraday with a plan: take Faraday’s powerful [Persona](/docs/abstractions/persona_sets) data and make it even easier for marketers to leverage. And armed with skills in statistics, math, and understanding of client marketing challenges, they took on one of the most common hurdles our clients face—how to identify insights that drive results.

### Take a look at the interview: 

<iframe
  width="560"
  height="315"
  src="https://www.youtube-nocookie.com/embed/oJ650NC2cp0?rel=0"
  title="Faraday interns built an even smarter Persona pipeline"
  loading="lazy"
  frameborder="0"
  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
  allowfullscreen>
</iframe>

## The problem: too much data, not enough insight

[Faraday’s Identity Graph](/features/faraday-identity-graph) provides over [1,500 consumer datapoints](/leaderboard), and our [Persona](/docs/abstractions/persona_sets) feature organizes audiences into distinctive [cohorts](/docs/abstractions/cohorts) (like "Middle-aged Mom Moira"). But marketers often need help identifying which traits matter for each Persona and how to act on them.

Faraday already offers several ways to tackle this challenge, from [forward-deployed data scientists](/blog/FDS-changes-the-game) to [model explainability tools](/blog/faraday-score-explainability) built into the platform. But our interns saw an opportunity to create a new workflow to automate the process: a tool that could not only automatically surface the most distinctive datapoints of each Persona, but also translate those datapoints into actionable messaging and product recommendations—ready to be automatically delivered into your CRM—without manual intervention.

## The solution: an automated pipeline

The interns designed a pipeline that pulls Persona data from the [Faraday API](/docs/reference), identifies distinctive datapoints, and feeds them into [Perplexity](http://perplexity.ai) AI. From there, Perplexity generates tailored messaging suggestions, product recommendations, and even market sizing insights—all mapped back to the Persona’s unique profile.

The final output? A clean, shareable marketing report that makes complex consumer data immediately usable. No spreadsheets. No guesswork. No manual data sifting.

[Download sample report \#1](/images/downloads/sample-persona-report-1.pdf).

## How it works

To measure how distinct each datapoint is across Personas, the team used two core metrics:

* Energy Distance for continuous variables like income or age  
* Total Variation Distance for categorical datapoints like gender or household type

These tests compare distributions across every Persona pair, flagging the datapoints where a Persona stands out most. The process is statistically grounded, with hypothesis testing and p-values to ensure real, meaningful differences are surfaced.

Once the key datapoints are identified, they’re passed into Perplexity AI along with client-specific context (like a brand website). The result? A few paragraphs of tailored content that includes:

* A narrative summary of the Persona  
* Marketing language suggestions  
* Recommended products  
* Market size estimations

All compiled into a client-ready report with citations.

[Download sample report \#2](/images/downloads/sample-persona-report-2.pdf).

## Turning Personas into action

The real win here isn’t just technical—it’s strategic. Marketers don’t want a firehose of 1,500 datapoints washing over them at once, they want to know:

* What makes this Persona unique?  
* How should we talk to them? 
* What should we sell?

This project answers those questions automatically—bridging the gap between complex analytics and real-world execution.

#### For instance

Imagine you’re a DTC skincare brand, exploring expansion into a more mature market segment. You’re already using Faraday to generate Personas, and one of them—“Self-Care Susan”—represents health-conscious women in their 60s who regularly purchase wellness products online. With this new pipeline, your team can instantly uncover what makes Susan unique (say, high engagement with plant-based ingredients and interest in loyalty programs), along with AI-generated messaging tailored to her values and product suggestions rooted in actual purchase behavior.

Suddenly, instead of wading through hundreds of datapoints or manually brainstorming campaign copy, your marketing team is armed with a ready-to-use report: what to say, what to sell, and why it’ll resonate.

It’s a leap from data to decision—saving time, improving targeting, and increasing campaign impact.

## Special thanks

Big thanks to our incredible interns, [Kayley](https://www.linkedin.com/in/kayley-watson/), [Zach](https://www.linkedin.com/in/zach-fu/), and [Xander](https://www.linkedin.com/in/alexander-swann/)—as well as Middlebury College—for their fantastic work. This is only the beginning, but it's already showing what happens when you combine statistical rigor with real-world marketing needs.

## Time to get started

Want to learn more or hear how these powerful new Persona pipelines could benefit your company? [Reach out](https://faraday.ai/talk-to-sales)\!

Faraday’s interns built an automated pipeline that analyzes Persona datapoints and generates ready-to-use marketing reports—turning complex data into clear messaging, product recommendations, and strategic insights.

Faraday’s interns built an even smarter Persona pipeline, here's how it works

It’s tempting to think of ROI analysis as a simple math problem. Plug in the numbers, calculate the return, and call it a day.

But the truly specialized secret to great ROI isn’t in the arithmetic; it’s the methodology and strategy that underlie and inform the analysis. It’s knowing *where* to look, *what* to measure, and *how* to choose the right approach for the situation. 

At Faraday, we don’t start our ROI analyses by creating an equation. We start by picking the right tool from the toolbox. Different tools unlock different kinds of answers. In our last blog, we made the case that [ROI isn’t a scorecard—it’s a strategy](/blog/roi-isnt-a-scorecard-its-a-strategy). This post digs into the next layer: how we measure ROI in a way that actually reflects the individual strategic value of your campaigns. 

And that starts by understanding which is the right method for the job.

## ROI isn't just about math, it’s about methodology

The actual math behind ROI analysis is pretty simple. You’re mostly dealing with addition, subtraction, multiplication, and division. In this case, complexity comes not from the operations themselves, but how we choose to apply them.

[![Comedic GIF showing arithmetic operations](/images/blog/mathishard.gif)](/images/blog/mathishard.gif)

An ROI specialist knows which data points matter, how to structure the comparison, and what kind of baseline you’re using to judge performance. In other words, the real work isn’t in crunching the numbers; it’s in designing the analysis.

And importantly, different ROI methods exist for a reason. Each one comes with trade-offs, and the right choice depends on your goals, your timeline, and the level of precision you need.

## Common "tools" in the ROI toolkit

There’s no single “best” way to measure impact. It depends on the shape of the campaign, the outcome you care about, and how precise your measurement needs to be.

Different methods are used depending on what you're measuring, what kind of attribution you need, and what trade-offs you’re willing to accept.

#### 1\. Holdout testing (A/B testing)

**How it works:** A holdout test randomly splits your audience into two groups, one that receives the intervention, and one that doesn’t. Then simply compare the outcomes.

**Advantages:**

* Delivers highly reliable attribution. You can isolate the effect of the intervention with minimal noise.
* Especially useful when you need clear proof of impact—for example, before rolling out a new campaign strategy.

**Disadvantages:**

* You’re intentionally withholding the (potentially better) treatment from part of your audience, which can mean sacrificing short-term gains.
* Longer-term metrics like LTV can require months or years of tracking, which slows down decision-making.
* Can be difficult to set up for more integrated processes.

**How this might look in practice:** A home services company wants to evaluate the impact of a new predictive lead scoring model. To measure its effectiveness, they randomly split inbound leads into two groups. The test group receives scores from Faraday, and the sales team uses those scores to prioritize outreach. The control group is handled as usual, without scores. After 30 days, the test group shows a 15% higher conversion rate. Because the only variable that changed was the introduction of scoring, the team can confidently attribute the improvement to Faraday’s model—and deploy it more broadly.

#### 2\. Longitudinal studies

**How it works:** These studies measure a key performance indicator (KPI) before and after an intervention, and attribute any change to the strategy.

**Advantages:**

* Easier to implement when the change affects a system or workflow that can’t easily be split, like internal operations.   
* No need to create and manage control groups.  
* Can continue tracking performance indefinitely without missing out on performance benefits.

**Disadvantages:**

* Harder to separate the signal from the noise. External factors like seasonality, sales events, or even weather can cloud the results.

**How this might look in practice:** Picture a credit union using Faraday to launch a predictive direct mail campaign aimed at promoting HELOCs. Since they want to reach the entire audience, they don't create a holdout group. Instead, they measure HELOC applications for eight weeks following the campaign and compare that to the eight weeks prior. Applications increase by 25%, and with no other major marketing efforts running in that window, the credit union sees a strong directional signal that the campaign worked.

#### 3\. Relative performance improvement studies

**How it works:** This method builds on a longitudinal approach, but instead of simply comparing “before” and “after” for one group, you compare the *change* in your test group to the *change* in a baseline group that wasn’t affected by the intervention.

In other words: both groups experience whatever else is happening in the world (seasonality, ad spend changes, etc.), but only the test group is affected by the treatment. By comparing the test group’s performance to the baseline group, you subtract out the “background noise” and can isolate the true impact.

**Advantages:**

* More resilient to outside variables. Since both groups are exposed to the same external forces, the comparison helps filter out unrelated effects.  
* Doesn’t require randomization—useful when you can’t run a traditional holdout test.

**Disadvantages:**

* Can be harder to explain to stakeholders unfamiliar with the method.  
* Requires a valid control group that closely tracks with the test group’s normal performance. If your baseline group isn’t steady or comparable, the whole thing falls apart.

**How this might look in practice:** Imagine a regional furniture retailer running a new predictive direct mail campaign in their Midwest region, while using their Northeast region as a comparison. Both regions are similar in customer base and seasonality, but only the Midwest receives the new campaign. During the test window, Midwest sales rise by 12%, while Northeast sales only increase by 2%. The 10-point gap is attributed to the campaign, with the unaffected region helping control for external factors like seasonal shopping trends or macroeconomic changes.

## Choosing the right tool for the job

Not every situation calls for the same approach, sometimes a "perfect" test isn’t practical or cost-effective. The best ROI analysts know how to match the method to the moment, balancing rigor with speed, and clarity with real-world constraints.

Here’s a quick cheat sheet to guide your choice:

* Use holdout tests when you need the cleanest attribution possible and you have time to run a structured experiment—ideal for testing new acquisition channels or proving the value of a bold strategy shift.

* Use longitudinal studies when A/B testing isn’t practical—like when rolling out changes to workflows, routing logic, or systems that touch your entire organization.

* Use relative performance studies when you can’t randomize, but you *can* find a comparable group or region to act as a baseline—helping you filter out external noise and isolate the true impact.

Choosing the right approach isn’t about checking a box—it’s about working with what you’ve got and building an analysis that supports better decisions.

## ROI is an art of trade-offs

Every method comes with trade-offs: between speed and precision, between statistical rigor and operational feasibility, between what you *want* to know and what you *can* realistically measure.

That’s why ROI analysis isn’t a checklist, but a craft. It requires judgment. True expertise means knowing when “good enough” is actually better than “perfect,” because it lets you act faster, test more often, and make decisions that still move the needle.

At Faraday, we don’t believe in one-size-fits-all measurement. Instead, we tailor ROI analysis to fit the strategy, timeline, and success metrics of each client. Whether that means running a formal holdout test, analyzing past performance, or finding a creative workaround, we help our clients make smart decisions grounded in evidence—not just instincts.

## Conclusion

At the end of the day, calculating ROI isn’t just a mechanical process, it’s a strategic one. The numbers only matter if they’re telling you something useful. And that usefulness depends on choosing the right tool, the right comparison, and the right trade-offs for your business.

Faraday’s approach is built around that idea. We help our clients go beyond surface-level metrics to get a clearer, more actionable picture of what’s working, what’s not, and what to do next. Whether you’re trying to justify spending, test a new channel, or make smarter bets for the future, we’ll help you measure what matters—on your terms.

Want to see how predictive insights and tailored ROI reporting can work together? [Let’s talk](/talk-to-sales).

Faraday’s strategic approach to ROI uses tailored analysis methods—like holdout testing, longitudinal studies, and relative comparisons—to deliver insights that actually reflect each client’s unique goals, constraints, and campaign impact.

Behind the numbers: The methodologies Faraday uses to turn ROI into value

In the world of home renovation financing—whether it's a new roof, solar panels, or energy-efficient upgrades—understanding a customer’s financial picture early saves everyone time. It tells you who to target, what to offer, and when to engage. More importantly, it reveals critical second-order insights—like upsell potential, churn risk, or even a household’s likely financing preference. But too often, teams wait until deep in the sales process to get that clarity, and often, by then, they’ve already invested precious time and resources in the wrong prospects.

## A smarter first signal

What if you had a way to gauge financial readiness right from the start? As soon as a prospect shows interest—downloads a brochure, fills out a form, clicks an ad—you’d already have a sense of whether they’re in a position to move forward. No sensitive data. No guesswork. Just strong, early indicators of capacity to convert.

That’s exactly what Faraday provides.

## How Faraday helps

Using ethically sourced, privacy-safe data from the [Faraday Identity Graph (FIG)](/features/faraday-identity-graph), our data platform delivers thousands of household-level, demographic, and behavioral datapoints—like financial capacity, payment patterns, homeownership details, and purchase activity—automatically into your CRM or workflows, surfacing deep and nuanced financial readiness signals. These datapoints come together to create a rich, predictive profile of each contact.

This empowers you to:

* Focus outreach on households most likely to engage  
* Reduce wasted effort on unlikely buyers  
* Accelerate deal cycles by prioritizing strong leads early

And financial signals are just the start. The same FIG data can forecast purchase intent, churn risk, and product fit, so your outreach isn’t just accurate—it’s relevant.

## Results you can bank on

Teams that layer FIG into their acquisition funnel see fewer wasted dials, sharper targeting, and faster closes. 

In short: less waste, more wins, and a growth engine that scales without ballooning acquisition costs.

Curious which signals matter most for your product? [Let’s talk](/talk-to-sales)\!

Faraday’s AI helps you identify financially ready prospects from the very first touch—cutting waste, accelerating sales, and scaling growth responsibly.

Gauge homeowner financial readiness from day one—with Faraday

[Dharmesh Shah](https://www.linkedin.com/in/dharmesh/) ([HubSpot](https://www.hubspot.com/)'s CTO) just [announced](https://www.linkedin.com/posts/dharmesh_breaking-news-hubspot-is-the-first-crm-to-activity-7336128750297735169-3O1-/?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAtKS-0BhomXJQm0PPBSMetJRw03HNXFZ2M) that HubSpot is now the first CRM natively connected to ChatGPT. 

This marks a major shift in how people will interact with their business data. Instead of clicking through dashboards or waiting on reports, users can now ask their CRM complex questions in plain English—and get instant answers. It’s a breakthrough in accessibility, speed, and strategy.

But while the interface is changing, the fundamentals aren’t. AI can only work with the data it’s given. So if your CRM is full of low-quality, outdated, or incomplete records, your shiny new chatbot will still give you shallow, outdated, incomplete answers.

## Your CRM can't predict the future if it's stuck with bad data

Imagine you're a CEO checking in on your sales pipeline. You fire up your shiny new CRM chatbot and ask, "Who are our warmest leads right now?" It spits out a list of accounts that sort of resemble last year’s ICP—based on a handful of clicks, a webinar signup, maybe a stale lead score from Q4. No context, no nuance, and no real signal. It’s not business intelligence, it’s data theater.

On the flip side, if your CRM is enriched with high-quality behavioral data and real-time propensity scores (delivered as custom datapoints) from a platform like Faraday, the response gets sharper: "These households show high intent for solar based on how similar they are to the last 5 deals you sold—high interest in environmental causes, EV ownership, and similar income levels. Prioritize them via SMS, and afternoons work best." Now that’s useful.

## Good AI needs great data

Everyone’s racing to integrate ChatGPT into their stack. But very few are thinking beyond the UI. The big unlock isn’t just asking better questions, it’s giving AI better context.

That’s where platforms like Faraday come in. We bring:

* Thousands of predictive datapoints from the [Faraday Identity Graph (FIG)](https://faraday.ai/features/faraday-identity-graph), including behavioral signals like payment habits, shopping styles, and lifestyle indicators.  
* Campaign-ready propensity scores that predict conversion, churn, upsell potential, and more.  
* Powerful consumer segmentation and personas that help you tailor messaging, creative, and channel strategy to match how real people behave—not just who they are on paper.  
* Privacy-safe enrichment that keeps your customer data siloed and secure.

## Better inputs, better outcomes

So yes, talk to your CRM. Ask it for trends, next steps, and hot leads. But if you want answers that are actually actionable, make sure your data is ready to support them.

Better interfaces are exciting. But better inputs are what make them work.

Want to see how smarter data makes AI work harder? [Let’s talk.](https://faraday.ai)

Smarter CRMs need smarter data—because even the best AI can’t deliver useful insights if it’s working with outdated or incomplete records.

Why smarter CRM experiences need smarter data

[![predictor leaderboard](/images/blog/predictor-leaderboard.png)](/images/blog/predictor-leaderboard.png)

We just launched something we’re really excited about: the [Faraday Predictor Leaderboard](/leaderboard). It’s a live look at the most consistently predictive traits in our platform, based on thousands of AI models and billions of real-world events.

You can filter by industry and use case, so whether you're in solar or e-commerce, doing lead scoring or churn prevention, you see what relevant-to-you traits are driving results, today. Things like “recent mortgage inquiry” or “owns a pool” aren’t just trivia—they’re signals that real models are using to generate lift.

In other words: the leaderboard gives you a peek at what’s driving value across the Faraday predictive universe, in real time.

And the takeaway? You don’t have to guess what traits matter anymore. The leaderboard shows you what’s working *right now*—so you can shortcut the discovery process and zero in on the signals that are already driving lift across industries like yours.

## How the Signal Index works

When you look at the leaderboard, the first thing you likely notice is the signal index. After all, it is the first column, but what exactly does that mean? 

Each trait on the leaderboard is assigned a signal index—a relative measure of how often it appears as an important predictor across thousands of live Faraday models. It’s not a raw number or percentage, but a way of showing which signals are standing out right now compared to others. This approach, sometimes called "indexing," is common in benchmarking and lets us highlight what’s rising to the top across industries and use cases.

## It all starts with FIG

Behind the scenes of the Predictor Leaderboard is one of the most powerful engines at Faraday: the [**Faraday Identity Graph (FIG)**](/features/faraday-identity-graph). FIG is our proprietary graph of nearly the entire U.S. adult population, connecting thousands of behavioral, demographic, and life event traits to real individuals. It’s how we detect stable, predictive signals that drive meaningful outcomes—like improving retention in financial services, increasing acquisition in solar, or boosting reactivation in e-commerce.

## So what exactly is a "trait"?

At Faraday, a trait is a specific detail about a person that helps explain their behavior—things like whether they’ve recently moved, have kids at home, or use a certain kind of credit card. When our models spot consistent patterns between these traits and real-world outcomes, they become powerful predictors of what someone might do next.

The traits on the leaderboard aren’t just interesting facts, they’re there because they’ve proven, across live campaigns, to consistently drive results. They help our models understand not just what someone did, but who they are and what matters to them.

So while the leaderboard gives you a snapshot of what’s working today, it also reveals the deeper, often surprising, behavioral signals powering our predictions.

## How to use the leaderboard

Think of the Predictor Leaderboard as a window into how Faraday models actually work.

It’s not a tool for tweaking models or choosing traits—in fact, all Faraday deployments already include built-in explainability, so users can see what’s driving predictions in their own campaigns. Instead, the leaderboard is a live demonstration of the kinds of traits that consistently drive predictive lift across industries and use cases.

If you're considering using Faraday, it gives you a real-world preview of the kinds of signals our models uncover—like how “dwelling type” shows up in solar acquisition, or how “shopping style” influences reactivation in e-commerce.

You’re not picking traits. But you are seeing what matters—and that insight can inform how you think about your audience, your positioning, and the outcomes you want to drive.

## So what’s trending this week?

Here are the top 5 traits currently driving predictions across Faraday:

1. **Shopping styles** 🛍 How a household prefers to shop (online, in-store, catalog, etc.). This trait is dominating campaigns that aim to personalize outreach based on behavior—especially in e-commerce and omni-channel retail.

2. **Age** 🎂 Simple but powerful, age is still one of the strongest predictors of conversion, churn, and reactivation, across almost every industry.

3. **Dwelling type** 🏡 Is it a single-family home? An apartment? A duplex? This trait is crucial for verticals like solar and insurance, where property type impacts eligibility and likelihood to act.

4. **Gender** ⚧ When used thoughtfully, this trait helps tailor messaging and product recommendations, especially in health, wellness, and fashion.

5. **Online household** 🌐 Does the household have a reliable internet connection? This trait is extremely predictive for digital product adoption and campaign engagement in rural and suburban markets.

Right now, these traits are being used to improve conversion rates, suppress churn, and drive smarter acquisition. That’s what the leaderboard shows: what’s working, right now, across real businesses and real campaigns.

## Iteration is the key

The leaderboard isn’t static—and that’s the point. Traits rise and fall, and we track those shifts obsessively. Not just because it’s interesting, but because it’s essential.

Getting prediction right isn’t about one great model—it’s about improving with every pass. That’s why we monitor trends over time, ask what’s changing and why, and use those insights to refine how our models learn.

This is core to how Faraday works: persistent observation, rigorous iteration, constant tuning. The result? Smarter campaigns, sharper targeting, and better results for our customers—week over week.

Want to see what traits are trending this week? [Check out the leaderboard](/leaderboard)\!

The Faraday Predictor Leaderboard offers a live, filterable view into the traits driving the most predictive lift across industries—giving you a real-time peek into what’s working in AI-powered marketing today.

Just launched: the Faraday Predictor Leaderboard

Sharing data for testing is a big step, and we know that sending anyone your closely guarded trove of customer information can be a little scary. That’s why, at Faraday, we take clear, deliberate steps to eliminate any risk to your records.

Here’s what to know about how we handle your data, in plain terms.

## NDA: At a glance

To start, we make sure the rules are clear on both sides: we’re bound by a mutual NDA, meaning confidentiality goes both ways. 

Here are some key points that keep you secure:

* As a data processor under data privacy laws, any data a client or prospect shares with us is used solely for providing our services or running agreed-upon tests. So when you send us your data, you can feel secure in knowing exactly what it will be used for and when.  
* Data security is our top priority. We’re [SOC 2 Type II audited](https://www.imperva.com/learn/data-security/soc-2-compliance/), read the next section to learn more.  
* Our mutual NDA ensures that any data you share is protected by strict confidentiality obligations.

## Security: We've got the receipts

At Faraday, we take data security seriously. That’s not just talk—we’re independently audited, fully encrypted, and built to comply with modern privacy laws. Whether you're testing data or running production campaigns, your information stays safe, confidential, and under your control.

Here’s how we do it:

* **SOC 2 Type II audited:** We undergo regular third-party audits to ensure our security controls are working as designed. This certification covers data protection, availability, and confidentiality across our systems.  
* **Compliant with major privacy laws:** Faraday operates as a data processor/service provider under regulations like GDPR and CCPA. That means we only use your data for the agreed-upon purposes—and never for our own gain.  
* **Fully encrypted:** All customer data is encrypted both at rest and in transit using industry-standard protocols. No shortcuts.  
* **Minimum internal access:** Access to data is tightly restricted, even within your own brand’s workspace. Only the team members directly responsible for running your project can view your data. (For example, the person writing this post—a marketer—has never seen a client record.)  
* **Siloed accounts:** Your data is never pooled with other clients’ data for modeling or analysis. Each account is kept fully separate, and customer-level data is only ever used to train models for your specific use case.

Want to dig deeper? Take a look at [our security page](/security).

## Validation: See it before you believe it

And why do we ask for your data before you buy? 

Transparency and evidence matter. At Faraday, we don’t believe in taking on clients we can’t generate value for. That’s why we conduct a complimentary holdout test by default, before you ever commit. This test only shows how well we can model on your data, with your data, so it requires an upload prior to signing up.

* We don’t just tell you our AI/ML models are working, we show you. To accomplish this, we run secure, real-data tests to validate Faraday’s performance before any commitment is made.  
* With these initial models, you’ll see the impact of our predictions on your specific use case, with your individual data (enriched with the Faraday Identity Graph), not just a generic demo.  
* No [black box](/blog/the-ai-blackbox-is-a-liability), no sales fluff, just results you can evaluate firsthand.  
* The results are yours to explore—you’ll see performance before making any commitment.  

Want to know how that works? Take a look at this blog about how [Faraday validates our models using your unique data](/blog/holdout-testing-with-faraday).

## In conclusion

Protecting your data is one of the most important things we do at Faraday. Our platform doesn’t work unless your data is safe—and we take that responsibility seriously. Hundreds of brands have trusted us with their data, and we’re proud to say this is one area where we consistently shine.

If you still have questions or concerns, don’t hesitate to reach out. We’re here to help.

Faraday takes a variety of measures to protect your data during pre-purchase model validation, here's the TLDR.

How Faraday protects your data during testing

Data appends—a process by which we add third-party data to what you already know about your customers—can ramp up your targeting, personalization, and market research. It’s one of the most effective ways to give your campaigns more context and reach. We’ve written before about [how Faraday handles appends](/blog/data-appends-blog), but there’s a follow-up question worth asking:

We’re not the only company offering these services and products. So what makes our brand different?

Here’s how we stand out:

### 1\. Best user experience—for developers and the rest of us

Whether you want to enrich a few records or run appends across millions, our modern [API](/docs/reference) and clear [documentation](/docs) make it easy to get started. You don’t have to worry about sending files by SFTP and waiting days for fulfillment. We’ve designed our platform to be fast, fully automated, transparent, and developer-friendly.

### 2\. High-quality data, ready for modeling

We source data from top-tier providers with robust coverage of U.S. adults, households, and consumer behavior. But we don’t stop there. We also clean, standardize, and organize every field to make it useful for AI and ready for immediate predictive modeling. You get reliable data that’s immediately actionable.

### 3\. Expert support to make it easy

When you hit a roadblock, we’re here to help. Our expert support team works closely with your team to ensure onboarding is smooth and your integration runs without a hitch. Moreover, our data science team is “forward-deployed,” ensuring that whatever help you need will be accessible, whether you’re troubleshooting an API call or just need guidance on best practices, we’re here to back you up.

## Less time managing data, more time using it

No one gets into marketing to build pipelines and dedupe records all day. From sourcing to setup to syncing, Faraday handles the grunt work so you don’t have to. The result? Less time spent fiddling with infrastructure, more time acting on insight.

Want to see what our data append services can do for you? [Let’s talk.](/contact)

Faraday’s data append services stand out by combining a seamless user experience, AI-ready high-quality data, and hands-on expert support—so you spend less time managing data and more time using it.

What sets Faraday’s data services apart?

If you read our last blog, [What’s in a deployment? How to read your Faraday outputs](how-to-interpret-your-outputs), you’ve already figured out what comes out of Faraday; now it’s time to understand how to shape it. While that post broke down the different types of payloads you can get from Faraday, this time, we’re going one level deeper: into the deployment settings themselves. 

Think of this as a user-friendly guide to all the options you might see when setting up a deployment—from filters to formats, geography to structure, and beyond. These settings help ensure that your predictions don’t just look good in a spreadsheet—they’re ready to plug into your actual tools, from CRMs to ad platforms.

If you've ever wondered what settings like "representation format," "add geometry," or “deployment analysis” actually do—or how they impact your final output—this blog is for you.

## But first, what’s a deployment again?

[Deployments](../docs/abstractions/deployments) (called “targets” in the API) are how you tell Faraday where to send your predictions and what those predictions should look like when they arrive. They’re created within a pipeline and allow for detailed customization to make sure the output fits your intended use case—whether you’re running a digital ad campaign, syncing data back into a CRM, or creating a list for direct mail.

### 1\. Where your predictions go

The first decision you make when creating a deployment is choosing its destination. This could be a Faraday-managed connection (like your CRM, ESP, or ad platform), a location in your own infrastructure (like a cloud bucket or database), or just a downloadable CSV. This is the foundation—everything else shapes what gets delivered. If you’d like to see a CSV broken down, check out that [last blog](how-to-interpret-your-outputs) we mentioned\!

### 2\. What your predictions look like

#### Representation format

In the app, we define this as the following: “Choose how you want the pipeline's output to be formatted for this target."

Think of representation format as the style or privacy level of your output—whether it’s raw, anonymized, or summarized. Deployments can be configured in a few different formats depending on how you plan to use the data:

* **Hashed**: This is the default format, typically used for ad platforms. PII is hashed to protect identity while allowing for matching.  
* **Referenced**: This format lets you use your own internal identifier to merge the data back into your system.  
* **Aggregated**: Useful for geotargeted ads or planning, canvassing, direct mail and more, this format summarizes how many individuals fall into key groups (like a persona or outcome) per geographic area. You’ll get a row per geographic area, with counts of people per persona or outcome. In this row, data can be aggregated into the following categories: ZIP code, census tract, carrier route, county, metro area, state, etc.  
* **Identified:** This format includes direct personal identifiers like name and address, allowing you to activate immediately through mailers, call centers, or CRM integrations. Because this format exposes PII, it’s only available in secure workflows with appropriate safeguards and permissions in place.

#### Column headers

You also get to choose how the column headers are labeled:

* **Machine-friendly** headers are concise and consistent, ideal for automated ingestion. Useful especially for our API users.   
* **Human-friendly** headers spell things out a bit more, which can make it easier for marketers and other stakeholders to work with the data directly, especially in tools like CRMs or email platforms. For example, “`fdy_persona_set_{UUID}_persona_name`” could appear as “`fdy_persona_set_customers_persona_name`” in human-readable mode.

### 3\. Filters, limits, and structure tweaks

#### Filters

Filters allow you to narrow your deployment to just the segments of interest. You can filter by personas, outcomes (via percentile or probability), or even recommender results (such as top product matches). This is how you target only the individuals who matter most for a given campaign. For example, give me the top 10% of scorers for my outcome. 

#### Limits

Need to limit the number of people you're deploying to? You can set a top or bottom row limit—useful for campaign budgeting, prioritization, or suppression. 

**📘Note:** in preview mode, deployments are capped at 1,000 rows. We break down the difference between preview mode and a deployment later in this blog\!

#### Structure

You can also rename or reorder columns to better match the formatting requirements of your destination platform. For example, if you're sending a list to LinkedIn or Facebook, you can use one of our pre-formatted options for easy compatibility.

### 4\. Geography & “Add geometry”

When building a geotargeted campaign, geographic options and the “add geometry” setting come into play. You can define the geographic granularity—ZIP code, metro area, census tract, etc.—and include shape data for use in map-based planning or delivery platforms. This setting only applies to aggregated deployments. 

If you’d like more information about how to read these outputs, just look at [our recent blog](how-to-interpret-your-outputs) which broke down how to read the labels\!

[![Example of what an add geometry output might look like](/images/blog/add-geometry-output.png)](/images/blog/add-geometry-output.png)

### 5\. Deployment analysis

Deployment analysis gives you a snapshot of what’s inside your deployment before you send it off. It includes summary stats on key traits and geographic distributions, delivered as a downloadable PDF or accessible via the API. This can help you validate that the list aligns with your goals—for example, checking that you’re really hitting the right income bands or urban areas before launching a campaign.

📘 **Note:** Access to traits in deployment analysis depends on your account permissions. If you’re not seeing the traits you need, reach out to your account manager to learn more about available options.

### 6\. Score explainability

Finally, if you've selected prediction explanations during pipeline setup, your deployment can also include score explainability. This details which traits had the greatest influence on an individual’s predicted score. It’s useful for internal transparency, model evaluation, or even surfacing to customer-facing teams.

If you're not sure whether you've enabled or don’t know how to read it, reach out to your Faraday team, we’ll confirm or help turn it on.

### 7\. Preview mode vs. full deployment

Before launching a full deployment, it’s helpful to run a preview—and it’s important to understand how previews behave differently. In preview mode, your deployment is capped at 1,000 rows, no matter what filters or limits you’ve set. This cap exists so you can sanity-check your configuration without triggering a full export. Once you’re ready to go live, the full deployment will reflect your entire population and apply all settings as specified—no artificial row limits included.

## Wrap-up

Deployments are more than just the final step in your predictive workflow—they’re the bridge between insight and action. With the right configuration, you ensure your models aren’t just accurate, but actually useful—delivering the right predictions, in the right format, to the right destination.

A practical guide to customizing Faraday deployments—from filters and formats to geography and output structure—so your predictions arrive ready for action.

How to shape your deployments: a guide to filters, formats, and more

If you’re a marketer asking how your team can qualify and prioritize leads more effectively, you’ve probably heard about predictive lead scoring. But what actually makes it different from traditional lead scoring, and is this ‘upgrade’ worth it?

Well, it’s 2025, and nobody’s got time for rhetorical suspense: yes, predictive lead scoring is a major upgrade, and yes, it’s worth it. Let’s break down why. 

## Before we dive in

Our CTO, Seamus Abshere, recently published a deeper technical breakdown of why simple scoring systems like RFM and first-party data alone aren’t enough to guide modern marketing strategies. That blog walks through the data science behind predictive scoring and why it outperforms old-school heuristics.

This blog aims to take that same content and break it down for non-technical readers, without the code samples or statistical deep dives. But if you’re feeling extra brainy today, or just want to try to understand the concepts like an expert data scientist would, [you can find Seamus's original post, “Why first party data (and RFM) is not enough”, here](/blog/why-first-party-data-and-rfm-is-not-enough).

## What is lead scoring?

Lead scoring is the process of ranking leads to determine how likely they are to convert into customers. This helps sales and marketing teams focus their time and resources on the people most likely to say “yes.”

There are two main approaches: traditional and predictive. Each aims to support conversion efforts, but they differ fundamentally in how they evaluate leads.

### Traditional vs. predictive lead scoring: A quick comparison

To understand the evolution from traditional to predictive lead scoring, it's helpful to see the differences laid out side by side:

| Feature | Traditional Lead Scoring | Predictive Lead Scoring |
| ----- | ----- | ----- |
| **Method** | Rule-based (manual point systems) | Machine learning trained on past outcomes |
| **Data used** | Basic firmographics, behaviors, form fills | Hundreds of behavioral, demographic, and contextual signals |
| **Scalability** | Manual tuning required per campaign | Fully automated, adaptable, and always learning |
| **Accuracy** | Assumptions-based, subjective | Outcome-driven, empirically validated |
| **Maintenance** | Static, often neglected | Continuously improved via retraining |
| **Transparency** | Clear but simplistic | Advanced but explainable (e.g., model cards) |

This comparison highlights how predictive lead scoring offers deeper insights, broader data coverage, and greater efficiency—without the manual overhead.

## Why smart CMOs are shifting towards predictive

With the complexity of today’s customer journeys and an explosion of marketing channels, relying on static, point-based scoring just doesn’t cut it anymore.

Traditional scoring is great—if it’s 2008\. But in 2025, teams are managing thousands of signals across channels, and the limitations of hand-crafted scoring systems are showing:

* **They can’t scale**—manually assigning points doesn’t work across product lines or geos.  
* **They’re biased**—they reflect gut instinct, not real data.  
* **They’re static**—the model that “worked” last quarter might be off-base today.

Predictive lead scoring flips that script. By analyzing your historical data—who actually converted, when, and why—machine learning models generate scores for new leads that reflect real patterns, not assumptions.

This shift enables marketing and sales teams to act faster and with greater confidence, knowing their lead rankings are grounded in evidence.

## How Faraday does predictive lead scoring differently

Of course, not all predictive models are created equal. At Faraday, predictive lead scoring isn’t just a model—it’s an integrated strategy designed for accuracy, usability, and transparency.

We help brands:

* **Enrich leads with real-world context** using the Faraday Identity Graph (240M+ U.S. adults)  
* **Train custom conversion models** based on your actual outcomes—not someone else’s benchmarks  
* **Deploy scores in real time** into CRMs, ad platforms, and lead routing systems  
* **Understand what’s working** with model transparency and segment-level insights

The goal is not just to predict who is likely to convert, but to help your team understand why they’re likely to convert—and how you can act on that knowledge.

## Common questions (and misconceptions)

As predictive scoring becomes more popular, a few key questions tend to come up. Here’s how we typically address them—drawing from our own platform and our CTO Seamus Abshere’s deeper technical dive on the topic.

#### “Isn’t predictive AI just a black box?”

This is one of the most common concerns we hear, and it’s a fair one. Many predictive tools offer opaque outputs with no clear path to explain how a lead was scored. At Faraday, we’ve made transparency a core design principle. Every model we build includes:

* Model explainability breakouts that document the data used, what the model was trained to predict, and how well it performed  
* Feature importance scores that show which attributes are driving conversion likelihood  
* Segment insights that break down what’s working and why in human-readable terms

If you want to dig into the technical mechanics of explainability, [this post from Seamus](blog/why-first-party-data-and-rfm-is-not-enough) goes deep on how we make models transparent and actionable, not just accurate.

#### “What if I don’t have enough data?”

Another myth. The truth is, most brands have more data than they think, they just need help unlocking it. And when first-party data really is sparse, Faraday fills in the gaps with [enrichment](/blog/identity-matching-makes-or-breaks-predictions).

We tap into our proprietary [Faraday Identity Graph](/features/faraday-identity-graph) covering 240+ million U.S. adults, enabling your models to learn from behavioral and contextual signals beyond your CRM. This lets you:

* Model outcomes even with limited internal history  
* Boost accuracy by adding real-world context  
* Reach prospects with higher confidence

Predictive lead scoring doesn’t require perfection—it just needs patterns. And sometimes, those patterns are hiding outside your own CRM.

Take one client, for example: Bee’s Wrap.

They were able to take their targeting to the next level by tapping into third-party data through Faraday.

## How Bee’s Wrap went beyond demographics

[Bee’s Wrap](https://www.beeswrap.com/), a sustainable food storage brand, needed help identifying new retail partners—but traditional targeting methods like household income or zip code weren’t cutting it. They turned to Faraday to build predictive personas based on actual behavior, not just surface-level traits.

Using third-party behavioral data, Faraday identified nuanced lifestyle patterns—like eco-consciousness and repeat purchase behavior—that wouldn’t show up in first-party data alone. That insight helped Bee’s Wrap secure distribution in over 550 locations of a major national retailer - you might've heard of them, they're called Target.

It’s a perfect example of why modern scoring needs to go deeper than form fields or simple demographic filters. 👉 [Read the full story](/blog/bees-wrap-persona-analysis)

## Want to see how your leads would score?

If you’re curious how predictive lead scoring could work with your data, we’d love to show you. Reach out to see what it looks like in practice—and how it can plug directly into your workflow.

A non-technical guide to why predictive lead scoring outperforms traditional methods—and how Faraday makes it transparent, scalable, and ready to use.

Predictive vs. traditional lead scoring, for dummies

At Faraday, transparency and explainability aren’t just ideals, they’re a core and ever-present aspect of our product strategy. We believe that understanding how and why predictions are made is critical to building trust in AI. That’s why we’re continually expanding what you can see and do inside the platform.

In a [previous post,](https://faraday.ai/blog/what-is-explainable-ai-why-is-it-important) we outlined how we expose the various steps we undertake—through explainability reports and other transparency measures—to help you understand the what and the why of your predictions. But now, we’re going a step further.

## Predictive modeling isn't magic, it's strategy

For every [Outcome](https://faraday.ai/docs/abstractions/outcomes) you define in Faraday, we build hundreds of models using a variety of strategies. These strategies define how we create candidate models, and after rigorous cross-validation, the best performers are promoted to production. 

In Faraday’s API, a *strategy* is a specific configuration or approach for building a predictive model. It may define which data sources to use, how to segment the population, and what modeling technique to apply. Strategies are automatically applied and tested behind the scenes as part of our modeling pipeline.

While this information was always available, until now, it appeared only in the technical report, buried, and inaccessible to machines. But with our latest release, that changes.

## What’s new

### API

The API for `GET /outcomes/:id/analysis` now includes a `strategies` object that lists all strategies used in the Outcome. Each includes:

* A unique ID and slug  
* Strategy name and description  
* Providers (e.g. Faraday Identity Graph, self-provided)  
* Experimental flag 

If you're inspecting results for specific individuals, you can now trace exactly which strategy applied to them.

### UI

This information now also shows up in the Dashboard. Choose one of your Outcomes, then find a new “Strategies” tab in the performance reporting.

📘 *Note:* Strategy metadata will only appear for newly generated Outcomes. Older Outcomes may not include this information unless reprocessed.

## Here’s why it matters

This update makes model strategy metadata available to humans and automations alike, enabling more transparent audits, better debugging, and smarter automation for advanced users.

It also surfaces a key part of the Faraday platform that's typically invisible: the structured experimentation that goes into every prediction, and that’s so central to our work, it’s literally where we got our name (but enough about [Michael Faraday](https://en.wikipedia.org/wiki/Michael_Faraday) and his experiments)\!

If you're building automation on top of Faraday or just want to better understand what goes into your Outcomes, this update is for you.

And if you want to learn more, ask your account manager, or visit [the Outcome API documentation](https://faraday.ai/docs/reference/getoutcomeanalysis)\!

Faraday now surfaces the modeling strategies used to build Outcomes—via API and dashboard—bringing deeper transparency and auditability to how predictions are made.

Product