Imagine this: You’re a brand with a list of leads, but no real way to tell which ones are actually in a financial position to become high-value customers. So you treat everyone the same. That means wasted spend, low conversion rates, and missed opportunities when your best reps chase the wrong people—or when a strong prospect drops out late in the funnel due to credit issues.

Now imagine you could suppress just the bottom 10%—the folks least likely to convert, based on financial behavior and purchasing power—without pulling a single credit score.

That’s where **Credit Score Proxy** comes in.

## So what is Credit Score Proxy?

Credit Score Proxy is a relative marketing value ranking. It segments 120 million U.S. households into 12 rank-ordered categories (A1 to E3), using behavioral and lifestyle data—like age, property characteristics, aggregate credit indicators, and more (we also offer a variant of this datapoint in which the 12 categories are collapsed to 5 more-manageable categories).

It can function as a predictive proxy for financial reliability, offering many of the same benefits as a **credit score** for marketers, without using actual sensitive credit data or requiring a credit pull.

This table shows how Credit Score Proxy tiers typically align with traditional credit score ranges (in the risk score column) but please note: these are illustrative estimates, not actual credit scores. Credit Score Proxy doesn’t use credit data or generate credit scores; these risk scores are included to help marketers understand how each tier relates to familiar financial benchmarks.

| Credit Score Proxy Rank | Illustrative Credit Score Range | % of Households in FIG\* | Marketing Profitability |
| ----------------------- | ------------------------------- | ------------------------ | ----------------------- |
| A1                      | 760                             | 17%                      | **Best**                |
| A2                      | 740                             | 10%                      | **Best**                |
| B1                      | 725                             | 10%                      | Above average           |
| B2                      | 710                             | 11%                      | Above average           |
| C1                      | 690                             | 11%                      | Average                 |
| C2                      | 675                             | 11%                      | Average                 |
| D1                      | 660                             | 10%                      | Below average           |
| D2                      | 650                             | 4%                       | Below average           |
| D3                      | 640                             | 4%                       | Below average           |
| E1                      | 625                             | 4%                       | **Poor**                |
| E2                      | 610                             | 4%                       | **Poor**                |
| E3                      | 590                             | 4%                       | **Poor**                |

**\* Note on distribution:** While the above table reflects approximate national distributions represented in FIG, the Faraday Identity Graph (FIG) shows a slight overrepresentation of higher-credit-score households and an underrepresentation of low-credit or underbanked individuals. This means your enriched dataset may lean more toward high-value prospects—helpful when prioritizing outreach, but worth keeping in mind for broad reach strategies.

So how should you think about using Credit Score Proxy in practice?

## What Credit Score Proxy isn’t

It’s easy to think of Credit Score Proxy as essentially a predictive credit proxy—and that’s not entirely wrong. But it’s also not quite right.

Unlike FICO or other regulated credit scores, Credit Score Proxy wasn’t built for lenders or compliance-heavy decisions. It’s designed for marketers who want to prioritize outreach based on a household’s likely value—not just financial risk.

It uses lifestyle, demographic, and inferred financial behavior to segment households by marketing profitability. No tradeline data, no credit bureau pulls—just smart signals modeled for outreach.

In short: Credit Score Proxy is inspired by credit scores, but optimized for marketing. It’s a broader, privacy-safe alternative that aligns with overall consumer value, not just credit risk.

## How Credit Score Proxy fits into Faraday

Faraday is a modern data platform that helps consumer brands grow by enriching their first-party records with **verified identity data**, curated **consumer datapoints**, and **custom AI-powered predictions**. At the heart of this is the [Faraday Identity Graph (FIG)](https://faraday.ai/features/faraday-identity-graph), our rich database that contains 1500+ unique datapoints on over 240 million U.S. adults and their households. This data is prediction ready, privacy safe, and sourced from some of the best providers in the industry.

We use the FIG to enrich your customer data by appending new information, giving you a deeper understanding of your audience and how best to engage with them. These enriched datapoints generally take three forms:

- **Verified identity data** — Fill in the blanks: name, email, phone, address. These verified identities form the foundation of every enriched record.  
  **Consumer datapoints** — Curated, industry-relevant traits like income, homeownership, household size, or age—plus prebuilt predictive scores such as likelihood to buy luxury goods or subscribe to streaming services. These datapoints make segmentation, targeting, and prioritization easy—even before layering on custom predictions.
- **Custom predictions** — AI-powered scores trained on your historical outcomes, like Likelihood to Buy, Best Product Recommendation, or Persona assignment. Built specifically for your brand, these models use your first-party data alongside the 1,500+ behavioral datapoints in the FIG. Unlike off-the-shelf predictive insights, they’re tailored to your goals and go-to-market motion.

**Credit Score Proxy** is a textbook example of a prebuilt predictive **consumer datapoint**, and like any other datapoint from the FIG, it’s added as a new column to your dataset—ready to drive smarter targeting, prioritization, and ROI.

With Credit Score Proxy in place, you can:

- Build audiences by selecting only the highest-value tiers
- Filter out low-likelihood individuals for cost-efficient targeting
- Route leads or assign reps based on expected value

It’s one of the fastest ways to improve performance without adding complexity—and without pulling credit.

## Credit Score Proxy in action

For example, here’s how [a leading direct-to-consumer home services brand used Credit Score Proxy to sharpen its acquisition funnel.](/blog/dtc-homeservices-uses-credit-score-proxy)

- **At the lead purchase stage**, they paired Credit Score Proxy with a custom predictive score to reject low-quality leads in real time—saving over **$500,000 in wasted spend** within five months.
- **At the appointment stage**, they used Credit Score Proxy tiers to flag households likely to fail credit checks, which were failing about **75% of the time** in lower tiers. By suppressing these leads, they freed up their reps to focus on high-value prospects.

The result: fewer wasted appointments, lower acquisition costs, and a more efficient sales funnel overall.

## Why it matters to you

Many of our clients need a way to infer financial standing without crossing regulatory lines. Credit Score Proxy gives you a privacy-friendly path to do just that—especially useful in industries like:

- Home services
- Solar and energy
- Education
- Debt settlement
- Financial products (without lending)

It’s one of the most effective ways to suppress low-value outreach and drive higher ROI on every campaign.

Want to learn how Credit Score Proxy works inside your workflow? [Let’s talk.](https://faraday.ai/contact)

Credit Score Proxy helps brands prioritize high-value prospects by ranking U.S. households into predictive tiers of marketing value—without using sensitive credit data.

Prioritize your most profitable prospects with predictive datapoints like Credit Score Proxy

The promise of "right message, right person" has guided marketers for decades. But the [static tactics](https://learn.microsoft.com/en-us/dynamics365/customer-insights/journeys/segments-static) we've relied on—segments, rules, and lookalike audiences—are no longer enough. They treat potential consumers as averages rather than as individuals, leaving revenue on the table. But the frontiers are moving (sorry [Terminus](<https://en.wikipedia.org/wiki/Terminus_(god)>)). Today, adaptive decisioning systems are leaving these limitations behind, learning in real time to adjust to each customer instead of locking them into a preset journey with the rest of their segment.

This is where [reinforcement learning](https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf) enters the picture: an AI methodology designed to personalize at the individual level by experimenting, adapting, and improving with every interaction. But not all reinforcement learning approaches are created equal—those with access to rich context start with a decisive advantage.

And that’s exactly where Faraday fits into the ecosystem. We provide the context reinforcement learning needs: the verified identity, essential consumer datapoints, and predictive insights that let these systems work faster, smarter, and more efficiently. So how does Faraday make this possible?

## How reinforcement learning works in marketing

Well first, let’s break down how reinforcement learning actually works.

At its core, **reinforcement learning (RL)** is a type of AI that learns by experimenting. Instead of relying on fixed rules or static segments, it tries different actions, measures the outcomes, and adjusts based on what works. Traditional segmentation might decide in advance that “all new homeowners get offer A” or “all loyalty members get email B.” RL, by contrast, doesn’t assume the same choice will work for everyone in a segment.

For instance, one new homeowner might be a bargain shopper who responds best to discount offers, while another might value premium experiences and care more about exclusivity than a perceived discount. Even though both fall into the same segment, they require entirely different outreach. RL recognizes those differences and adapts accordingly.

Two common approaches within RL are known as _bandits_:

- **Multi-armed bandit**: starts with no prior knowledge. A marketer might randomly test several subject lines in an email campaign and gradually shift toward the one that produces the highest open rate.

- **Contextual bandit**: uses additional information—like demographics, past purchases, or engagement history—to make more informed choices from the start. For example, it might send one subject line to long-time loyalty members and another to first-time shoppers, while still experimenting and refining over time.

**The key idea:** context gives reinforcement learning a head start. Instead of wasting cycles testing irrelevant options, the system begins with signals that already separate one customer from another—like income, household size, or likelihood to convert. That means it doesn’t just converge faster on the right actions, it also avoids costly missteps along the way and delivers more relevant outcomes from the very first interaction.

## The challenge: Contextual AI requires rich data

The challenge, however, is that contextual bandits are only as good as the data they’re given. And most brands don’t have enough first-party data to support them effectively.

This problem typically stems from three key issues:

- **Limited internal data**: Customer data in a CRM or CDP only goes so far. Without external signals, the system can’t distinguish between two lookalike customers.
- [**Cold start problem**](/stories/dtc-retailer): For brand new prospects, there’s no behavioral history at all. RL can’t guess what to promote without context.
- **Slow learning**: Even with some context, bandits learn by running real-world experiments. That takes time, which delays value.

So we get it, context is king, but where can I get all this juicy data?

## Solving the context gap with Faraday

Through our powerful [Faraday Identity Graph](/features/faraday-identity-graph) (FIG), which contains 1500+ consented and verified datapoints on over 240M consumers and their households, Faraday delivers the three layers of data that reinforcement learning systems require to be effective from day one. With these inclusions, instead of learning blindly, our platform gives your systems a decisive head start using:

- **Verified identity data:** Ensure the people in your dataset are real and reachable.
- **Essential consumer datapoints:** Curated attributes like homeownership, household size, and income that add meaningful depth.
- **Custom predictive datapoints:** Scores and models trained on your outcomes—likelihood to convert, churn risk, or best product recommendation—that deliver precision and business impact.

Together, these layers make your data both complete and actionable. FIG provides the breadth, enrichment provides the depth, and predictions provide the precision. That combination drives ROI in everyday campaigns—and it also accelerates emerging approaches like reinforcement learning.

**Which brings us to an important point:** the relationship between predictive modeling and reinforcement learning. These approaches aren’t competing—they actually strengthen one another.

### Predictions and reinforcement learning are better together

We established earlier that contextual bandits are a major leap forward because they use data to make smarter initial guesses, speeding up this process. But we can take this a step further. When you supercharge a contextual bandit with **predictive insights**—like a customer's likelihood to convert or churn—you create an even more powerful personalization engine.

The primary drawback of reinforcement learning is that it can be extremely slow in real-world applications. It needs to run countless experiments to learn. This is where predictive modeling acts as a powerful accelerator.

Instead of forcing the RL system to test every possible variable for every customer, Faraday’s predictive models first simplify the problem—a concept known as dimensionality reduction. Our models can identify high-level personas or critical attributes (like churn risk or likelihood to engage), allowing the RL system to:

- **Focus on a smaller set of key factors** for more targeted experimentation.
- **Prioritize customers who are already likely to respond**, rather than “swimming against the current” by testing offers on uninterested prospects.

In short, predictive models do the heavy lifting of finding the right patterns and people first. The RL system can then take over to fine-tune the details, like which specific message or offer resonates best within those pre-qualified groups. The result is faster time to value, more efficient personalization, and stronger outcomes.

## Making your data work for you

Reinforcement learning is a compelling example of how marketing is evolving toward more adaptive, individualized experiences. But whether you’re experimenting with the latest AI techniques or simply trying to run more efficient campaigns, the real question is the same: _is your data working for you?_

That’s Faraday’s mission. By making identity data reliable, consumer attributes accessible, and predictive insights easy to use, we turn static records into a living foundation for growth. With the right context in place, every system you plug in—reinforcement learning included—can deliver faster, smarter, and more measurable results. That’s what it means to make your data work for you.

Want to learn more about how Faraday’s data can power AI for your company? [Let’s talk.](/talk-to-sales)

Reinforcement learning promises real-time personalization, but it needs rich context to work—and Faraday provides the verified identity, consumer datapoints, and predictive insights that make it effective from day one.

The new frontier of personalization: Why reinforcement learning needs better data

Every marketer knows the feeling: you’ve invested heavily to drive demand, nurtured warm leads, and handed them off to the call center — only to watch conversion rates flatline.

The call center’s job is simple in theory: take warm leads and turn them into real dollars. But too often, reps are churning through lists, treating every lead the same, and burning time on the wrong prospects. The result? **Terrible conversion rates, frustrated teams, and wasted budget.**

## The real problem isn’t marketing — it’s targeting

Before you point the finger back at your CMO, it’s worth asking what really happens once a lead hits the call center.

The challenge might not be the number of leads or the skill of the reps — it’s whether the right prospects are even getting attention in the first place. Without a way to distinguish high-intent buyers from tire-kickers, reps waste valuable time chasing the wrong people while genuine opportunities slip away.

And the unfortunate reality today is that many call centers still operate on instinct and raw volume rather than intelligence, leaving conversion potential untapped.

## How predictive scoring fixes the problem

But it doesn't have to be this way anymore\! [Custom predictive datapoints](/blog/stop-buying-more-data-get-the-right-data) like **Likelihood-to-Convert** allow you to [score leads in real time](/blog/real-time-vs-batch-which-drives-roi), separating serious buyers from casual interest before they ever reach a rep.

Take [a national DTC home services retailer](/blog/dtc-homeservices-uses-credit-score-proxy) we work with as an example. They were seeing thousands of leads pour in, but their call center was overwhelmed and conversions lagged. Instead of asking their reps to just "work harder," they came to Faraday.

Together, we built a custom predictive datapoint using their own first-party-data as well as the [Faraday Identity Graph](/features/faraday-identity-graph) (FIG) which contains 1500+ datapoints on 240M+ US consumers and their households. This datapoint identified which households were most likely to purchase.

This allowed every new lead that entered the center to be automatically given a score on their likelihood to buy and the call center could focus its most experienced reps on those high-scoring prospects while still nurturing the rest with lower-cost resources.

The difference was immediate:

- **In 2 days:** 2% lift in contact rates
- **In 1 month:** 4% lift in conversions
- **In 3 months:** Predictive scoring became the nucleus of their tech stack — saving over $100K/month in wasted effort!

[![Diagram showing set rate vs. date](/images/blog/american-standard-chart.png)](/images/blog/american-standard-chart.png)

## Why it matters to you

For marketing executives at consumer brands, especially in high-consideration sectors like financial services, solar, and home improvement, this isn’t just a call center optimization trick.

It’s a way to:

- Protect marketing ROI by ensuring warm leads don’t go cold in the call center.
- Improve conversion efficiency without increasing ad spend.
- Build sustainable competitive advantage with predictive intelligence your competitors can’t replicate.

## Conclusion

Call centers don’t have to be a black hole where good leads go to die. By pairing your first-party data with predictive intelligence, you can ensure that your marketing investment actually turns into revenue. When you know which prospects are most likely to convert, you can transform your call center from a cost center into a growth engine. Smarter targeting protects ROI, boosts conversions, and builds lasting competitive advantage.

Find out the difference smarter lead scoring can make today. [Come say hi.](/talk-to-sales)

Predictive lead scoring transforms call centers from cost sinks into growth engines by ensuring reps focus on the prospects most likely to convert.

Leads dying on the call center floor? Here’s why you need lead scoring

You probably know Faraday for our powerful AI predictions. But before we get to the models, let’s talk about something more foundational: data.

AI is only as good as the data you feed it. And for our partners, it’s Faraday’s data services that are driving some of the biggest returns on investment.

## The problem

Most brands are swimming in data, but it’s incomplete, messy, or not built for decision-making. Identity gaps, missing datapoints, and a lack of predictive signals make it almost impossible to personalize outreach, optimize marketing spend, or build the data-driven features customers expect.

## The solution

Faraday acts as your modern data platform and predictive layer. We enrich your existing records with verified identity, curated consumer datapoints, and custom predictions—so your team always has the exact data you need to drive action. In short: we turn your existing data into a strategic advantage.

## The three pillars of the Faraday data platform

**Identity completion:** The first pillar is verified identity data. This is the foundation—filling in the blanks with name, email, phone, and address. With this in place, you can actually reach the people you want to talk to.

**Essential consumer datapoints:** The second pillar is essential consumer datapoints. These are curated, industry-relevant attributes like income, homeownership, household size, and age, drawn from the 1,500+ datapoints in the [Faraday Identity Graph](/features/faraday-identity-graph), which covers 240 million U.S. consumers and their households. We also provide prebuilt predictive datapoints like likelihood to buy luxury goods or subscribe to streaming services. Even before you bring custom AI/ML modeling and datapoints into the picture, these datapoints make segmentation and targeting straightforward and give you a much more complete picture of your consumers.

This also helps solve the [cold start problem](/stories/dtc-retailer). In other words, even if you don’t yet have large volumes of first-party data, these foundational datapoints give you enough signal to begin segmenting, targeting, and personalizing right away.

**Custom predictive datapoints:** The third pillar is custom predictions. These are AI-powered scores trained on your historical outcomes: Likelihood to Buy, Best Product Recommendation, Persona assignment, and more. Unlike off-the-shelf scores, these predictions are tailored to your brand and goals, built on your first-party data plus all 1,500+ datapoints in the Faraday Identity Graph. All of this is responsibly sourced, privacy-safe, and refreshed regularly to maintain signal quality.

## How the data is delivered

Enriched records don’t just sit in a report—they’re delivered directly into the tools your team already uses. You can access them in your CRM, ESP, lead platform, or warehouse in whatever format works best: batch uploads, clean APIs, or cloud shares. For certain use cases, like the ping-post process, we can even deliver enriched datapoints in real time through services like LeadConduit. That means you can avoid wasting money bidding on low-value leads and make smarter decisions on the fly.

## Why you need all three

Each pillar adds value on its own, but together they unlock a data foundation that’s accurate, actionable, and AI-ready. Consider a [case study from one of our DTC partners in home services](/stories/dtc-home-services). They were struggling with call center efficiency: too many missed connections and wasted calls. With identity completion, Faraday helped them verify phone numbers and addresses from website leads, so the call center could actually follow up. With essential datapoints, they could prioritize outreach to homeowners in relevant geographies. With custom predictions, they scored every lead on likelihood to convert—so agents could focus on the best opportunities first. The result was faster follow-ups, fewer wasted calls, and hundreds of thousands of dollars saved per year.

## Who this helps

Faraday supports consumer brands that want to enrich customer data, boost conversion rates, and eliminate wasted spend on low-fit leads. We also work with SaaS platforms and agencies embedding predictive data into their products to launch features faster and drive more client value.

## The takeaway

AI isn’t magic—it’s data, structured and trained to work for you. Faraday provides the building blocks: verified identity, essential datapoints, and custom predictions. Put together, they give your team the confidence to prioritize, personalize, and grow.

Want to see how Faraday’s varied datapoints can transform your funnel and drive value for your brand? [Let’s talk.](/contact)

Faraday helps brands grow smarter by enriching their data with verified identity completion, essential consumer datapoints, and custom predictive datapoints—delivered directly into their tools for more accurate, actionable, and efficient decision-making.

The three types of data that power smarter growth

Not all leads are created equal. When call center capacity is limited, knowing who to call first can be the difference between a good month and a great one. That’s where lead scoring comes in—helping you focus on the opportunities most likely to convert, while still working the rest of your pipeline with intention.

In this joint session, Faraday’s Dave Small and CallTools COO Chaz Tedesco unpack how predictive scoring and data enrichment work together to supercharge your outbound strategy. From ranking hot leads to surfacing insights you can use in your scripts, they share how to put your data to work in real time—whether you’re working fresh leads, reactivating older ones, or responding to inbound calls.

**From this session, you’ll learn:**

- What goes into a predictive lead score and how to tailor it to your goals
- Ways to enrich leads with demographic, property, and behavioral data
- How to prioritize leads during high-volume periods to protect conversion rates
- Real-world examples of outbound teams boosting results with smarter dialing
- How to integrate scores into your call strategy, cadences, and follow-ups

By combining Faraday’s predictive insights with CallTools’ dialing capabilities, you can turn raw data into actionable intelligence—and make sure every call moves you closer to a win.

<iframe width="560" height="315" src="https://www.youtube.com/embed/CBqqAR35A0g?si=VVFoDqRyFVkcNiN5" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>

Join Faraday’s Dave Small and CallTools COO Chaz Tedesco as they explore how predictive lead scoring and enrichment can help you prioritize the right prospects, improve conversion rates, and make every dial count.

Smarter dials: How lead scoring transforms your outbound strategy

The [Faraday Identity Graph (FIG)](/features/faraday-identity-graph) is the powerful, privacy-safe dataset that fuels everything we do, from predictive modeling and enrichment to identity resolution. It brings together hundreds of millions of U.S. consumer records from trusted partners, cleansed, enriched, and organized into over [1,500 actionable consumer data points](/leaderboard), which are ready to use [from day one](/stories/dtc-retailer). So whether you’re filling in your dataset or trying to figure out what your leads will do next, FIG delivers the complete, privacy-safe intelligence you need to power smarter outreach and better customer experiences.

We update FIG regularly to keep it fresh and reliable, but our latest release includes some pretty exciting new features in addition to our standard update, so we wanted to tell you about what’s going on in there. Here’s what’s new:

## 📈 Updated data from leading providers

We’ve incorporated the latest available data from the country’s best providers. This happens each time we update FIG.

## 👶 Better coverage on young consumers

This update significantly expands our coverage of younger adult populations—adding millions of new records for individuals aged 18–34, a critical segment for many brands seeking early loyalty and long-term value.

It also includes improved age sourcing and fewer inferred records overall, leading to sharper demographic and behavioral insights across the board. Whether you're targeting young renters, streaming enthusiasts, or first-time buyers, this release gives your models a more accurate picture of today’s consumers.

## 🧠 Smarter match boosting

[Match Boost](/blog/match-boost-improves-enrichment) is our identity resolution enhancement that improves your match rates by checking additional data sources when your records are sparse or messy. Instead of relying on a single source, it uses a fallback (or "waterfall") approach to find the best possible match.

With this update, Match Boost now works across both **batch** and **real-time** workflows—meaning better performance whether you're enriching large files or resolving identities on the fly. The upgraded pipeline is fully automated, so you’ll see stronger resolution and fewer missed matches.

This upgrade is included by default after Match Boost has been added to your account.

## 🧬 Multi-identity return

FIG now supports **multi-identity return**, meaning it can surface multiple validated contact points—like emails or mailing addresses—for a single individual when available. That gives you more flexibility in matching, targeting, and outreach across fragmented systems.

Contact your account manager to add this feature to your account if you’re interested\!

## All of this is already available at your fingertips

With improved demographic coverage and better underlying data, FIG now reflects real-world consumer complexity more accurately than ever—capturing a broader range of ages, life stages, and behavioral traits that matter when you're trying to reach the right people, in the right way.

If you’re already using Faraday, there’s nothing you need to do. These improvements are rolling out now and will begin powering your workflows automatically.

Curious how FIG fits into your customer data strategy? Let’s talk.

The latest Faraday Identity Graph update delivers sharper demographic insights, expanded coverage of young adults, improved real-time identity resolution, and multi-contact matching.

The Faraday Identity Graph just got even smarter

Whether you're scoring leads, personalizing outreach, or building omnichannel campaigns with predictive modeling, it all starts with identity. And if you can't confidently link a record to a real person, everything downstream—predictions, engagement, outcomes—starts to break down.

Faraday already offers powerful [identity resolution](/blog/payload-fallbacks) tools through the [Faraday Identity Graph](/features/faraday-identity-graph), which can do a lot with a little. Even sparse records like email-only or phone-only leads can often be matched and scored out of the box. But in high-stakes campaigns, every additional match counts and boosting that match rate, even slightly, can significantly impact your outcomes. 

So to make sure that match rate is not just excellent, but as good as possible, we’ve introduced a new feature, called **Match Boost**. It taps into additional third-party identity sources to improve match rates even further, especially on partial or hard-to-match records. Whether you're trying to expand reach, improve prediction coverage, or support downstream workflows that rely on complete identity data, Match Boost helps you go beyond “good enough.”

## Why match rate matters (more than ever) in 2025

[3rd party predictive models like Faraday’s](/blog/why-first-party-data-and-rfm-is-not-enough) provide deeper insight than their first-party-only alternatives, but they still run on identity matching, and live or die by their ability to effectively match customer records to their external datasets. When individuals in your customer data are loaded into Faraday and recognized—that is, successfully matched to the [Faraday Identity Graph](features/faraday-identity-graph), they’re enhanced with hundreds of rich datapoints. These new datapoints add fuel to your predictive models, allowing them to train on more information. Higher match rates mean:

* **More records scored** – fewer “unknown” rows languishing in the void.  
* **Sharper predictions** – more signals per person, which means better lift curves.  
* **Omnichannel reach** – physical addresses unlock direct mail, phone numbers power SMS, you get the idea.  
* [**Cracking the cold start problem**](/stories/dtc-retailer) – enriches brand‑new or sparse lists so models have enough context to make accurate predictions from day one.

The trouble? Many datasets are hard to match: a newsletter signup with only an email, a warranty card with just a phone, a loyalty file missing addresses—those single‑identifier records can still slip through the cracks and if that happens, your baseline match step stalls and your models lose context.

## Enter Match Boost

To solve this problem, we’re excited to share the latest feature added to the Faraday platform: **Match Boost**.

The Match Boost feature includes two distinct capabilities:

### 1\. Recognition enhancement for better modeling

Match Boost increases the portion of your customer data that Faraday can recognize and enhance with datapoints from the Identity Graph. That means:

* More records matched  
* More accurate and complete predictive models  
* Better prediction coverage—no more “no-score” results

Behind the scenes, Faraday uses a network of data providers, submitting *unmatched* records from your datasets to retrieve additional identity data. With additional/updated identifiers, we’ll be able to match even more of your data to FIG.

### 2\. Expanded identity enrichment for outbound engagement

Match Boost customers also gain access to identity data (like phone numbers and physical addresses) for deployment, enabling:

* Better channel coverage  
* Omnichannel activation from day one

[![Match boost diagram](/images/blog/match-boost-blog/persona-with-information.png)](/images/blog/match-boost-blog/persona-with-information.png)

## When would you use Match Boost?

So we get that Match Boost is powerful, but when, exactly is it the most useful? You’d reach for Match Boost when:

### 1\. Your input data is extra sparse

Think single identifiers—like just an email or phone number. Faraday can often match these, but Match Boost increases the odds by tapping into third-party identity sources.

### 2\. You need to engage on more channels

If you’re trying to run omnichannel campaigns but only have partial contact info, Match Boost helps fill in the gaps—like turning an email into a mailable household.

### 3\. You’re trying to maximize model coverage

Predictive models work best when more people are matchable. Boosting match rates means fewer “unknowns” and stronger lift curves.

### 4\. You want full enrichment—even for already-matched records

For clients with access to advanced features, Match Boost can run even on records already matched to Faraday’s graph, layering on additional identity details you wouldn’t get otherwise.

## Getting set up

If you're interested in adding the Match Boost feature to your Faraday account, contact your account manager to get set up.

### How it works in dashboard

1. If your account has Match Boost enabled, you’ll see a checkbox labeled ‘enrich this dataset with additional identity data where possible’ when creating or editing a dataset.

[![Match boost check box in dashboard](/images/blog/match-boost-blog/matchboost-enrich-button.png)](/images/blog/match-boost-blog/matchboost-enrich-button.png)

2. Faraday runs its normal graph match process.  
3. Any unmatched records automatically flow through Match Boost.  
4. Additional identity data is resolved and returned.  
5. These new identifiers inform model training and improve prediction coverage.  
6. You can view the impact directly in the dashboard—hover over the enrichment percentage in the dataset index view to see the lift.  

[![Match boost results pop-up](/images/blog/match-boost-blog/match-boost-display.png)](/images/blog/match-boost-blog/match-boost-display.png)

7. Whenever you make a new Deployment in Identified or Referenced mode, the output will automatically include identity data that was missing in your original dataset.

### How it works in API

Faraday’s API users can enable Match Boost for a dataset by including it in the `identity_providers` array when making `POST` or `PATCH` [dataset requests](/docs/reference/createdataset). This allows additional identity data to be resolved during the ingestion process, improving match rates and model performance.

```
{
  ...,
  "identity_providers": [
    { "provider": "fig" },
    { "provider": "match_boost" }
  ]
}
```

We’ll be publishing a full API how-to next week, so keep an eye out if you’re looking to integrate this into your workflows programmatically.

## Improve your predictive modeling, today

With Match Boost, your datasets stop freeloading and start pulling their weight. Contact your account manager to learn more, or if you’re not yet a customer, welcome\! [Come say hi to sales](/talk-to-sales) (they’re very friendly). 

Let’s make every record count, together.

Faraday’s new Match Boost feature improves identity match rates—especially for sparse or single-identifier records—by tapping into additional data sources, enabling better predictions and broader omnichannel engagement.

Match Boost improves enrichment coverage on sparse data

What if you could save over $100,000 every month, just by avoiding outreach to the wrong leads?

That’s exactly what [one debt consolidation firm achieved](/blog/debt-consolidation-company-saves-100k) with Faraday. Facing skyrocketing direct mail costs, they came to us looking for a smarter way to reach the right people without blowing their budget on low-intent leads.

To solve their problem, we helped them enrich their lead list with consumer data from the [Faraday Identity Graph](/features/faraday-identity-graph) and built an AI model to deliver each lead a custom predictive datapoint: likelihood-to-convert. With this in place, they started suppressing just the bottom 10% of their mailing—a segment they could confidently predict wouldn’t take action.

That small change made a massive impact: 
  * **Over 600,000 fewer mailers** sent each month
  * **\$100,000+ in monthly savings**
  * And **an extra \$20,000 in revenue** thanks to their reps focusing on better leads.

That’s a 10x ROI, without changing the offer or creative. Just smarter targeting.

But here’s the thing, this experience isn’t unique to this client. The debt settlement space is evolving fast. Rising lead costs, stricter compliance requirements, and shifting consumer expectations are pushing companies everywhere to find smarter ways to grow, target, and personalize. That’s where data and AI make all the difference.

Faraday helps companies identify and integrate the data their business needs to anticipate how their customers will behave. Whether you’re trying to maximize the value of your call center, prioritize leads, personalize outreach, or just reduce wasted spend, Faraday’s platform enables you to understand your audience more holistically and to act on accurate, validated predictions rather than just past performance. For you, that means more money, and less hassle.

## Core use cases for debt settlement and financial services clients

### Comprehensive data services

Nearly every Faraday project begins with data. Our platform [enriches](/blog/identity-matching-makes-or-breaks-predictions) your customer or lead records using the [Faraday Identity Graph](/features/faraday-identity-graph) (FIG)—a comprehensive, consented, and privacy-safe dataset covering over 1,500+ attributes on 240 million U.S. adults and their households. These datapoints include a range of industry-relevant indicators like debt load, household composition, mortgage status, and even shopping habits. 

Whether you're working with new leads or existing customers, this enrichment process not only fills in the gaps but it also adds new actionable data that ensures you’re ready for AI modeling. This data layer is the foundation for everything that follows. Without it, predictive scoring, segmentation, and personalization simply wouldn’t be possible.

Learn more about our [comprehensive data services](/docs/abstractions/data-appends).

### Predict who’s ready to engage

Faraday’s lead prioritization tools help firms move beyond instinct. Using advanced AI, we help brands optimize their lead conversion process by scoring based on their likelihood of converting. This starts the moment a lead identifies themselves—when they first share their contact information—and continues throughout the entire lead-to-customer journey.  By enriching each new record with FIG attributes, Faraday also avoids the classic [cold-start problem](/stories/dtc-retailer), delivering confident predictions from day one.

Learn more about how we [predict who’s ready to engage](/templates/lead-prioritization).

### Suppress unqualified or risky leads

Faraday helps teams reduce acquisition costs and improve ROI by identifying leads that are unlikely to convert—or may raise compliance concerns—before any outreach occurs. Suppression models ensure that reps and budgets stay focused on higher-quality prospects. This approach is especially powerful in direct mail, predicting which households are most likely to respond while cutting costs without sacrificing performance.

Learn more about how we [suppress unqualified or risky leads](/templates/lead-suppression).

### Segment smarter with behavioral Personas

Faraday’s AI-driven Personas group individuals based on lifestyle, values, and behavior patterns—not just age or income. These insights help with personalization and allow you to tailor messaging, tone, and timing to improve campaign performance across email, phone, SMS, and direct mail.

Learn more about how we [segment smarter with behavioral Personas](/templates/thematic-personalization).

### Recommend the right product, at the right time

Whether promoting a debt relief offer, a loan product, or financial counseling, Faraday can predict what product someone is most likely to engage with next. This allows teams to match offers to individual needs and improve adoption rates.

Learn more about how we [recommend the right product, at the right time](/templates/next-best-offer).

## Get in touch

Whether you’re a large national brand or a smaller operation, Faraday helps make every customer interaction count. [Reach out](https://www.faraday.ai/talk-to-sales) for a personalized walkthrough.

Faraday uses predictive AI and enriched consumer data to help debt settlement companies cut acquisition costs, prioritize high-intent leads, and drive smarter, more profitable outreach.

Save $100K/month with smarter targeting - how Faraday’s predictive AI datapoints are reshaping debt settlement

In our last blog in this series, we tackled a common question: [*When should I update my personas*](/blog/when-and-why-to-update-personas)*?* The answer, in short: almost never. Personas are a foundation—not a real-time dashboard—and you don’t pour new concrete every week.

But if that post answered the *when*, this one’s about the *what*. As in: How many [persona sets](/docs/abstractions/persona_sets) do I actually need? 

But it’s 2025 and we’re all very busy, so here’s the TLDR: **You almost certainly only want ONE persona set.** 

But for those of us who want a deeper dive, read on. 👇

## What is a persona set?

A [persona set](/docs/abstractions/persona_sets) is a small group of customer personas—each one representing a distinct cluster of your real customers. These personas are archetypes based on shared traits and behaviors, built from the people who have actually converted. They're the foundation for structured personalization across your brand.

So let’s clarify terms:

* A **Persona** is a single, representative profile within a set. Think "Urban Millennial Max" or "Suburban Saver Susan."  
* A **Persona set** is the full group of those profiles—usually 3 to 7 personas total—that collectively describe your customer base.

Personas aren't based on assumptions or hypotheticals. And they’re definitely not built around leads or website visitors. The reason is that personas need to be grounded in actual converted customers, you know the ones who said *yes*, not the ones who ghosted you. These people have the traits you want to seek out in new leads who you also want to convert.

The purpose of a persona set is to give your brand a coherent, actionable structure for engaging your audience. You use them to vary messaging, align creative, and personalize campaigns across the funnel.

## How do we build them?

At Faraday, we build persona sets using [enriched data](/docs/abstractions/datasets) and [k-means clustering](/blog/k-means-clustering-customer-personas). We start with your customer file—ideally recent customers—and enhance it with third-party traits from the [Faraday Identity Graph](/features/faraday-identity-graph), which includes demographic signals (like age, household size, income range), geographic markers, lifestyle and behavior data, and more. This rich, consented data allows our AI to surface patterns that wouldn’t be obvious from first-party data alone.

After we enrich your data, we use a method called *k-means clustering*, which automatically groups all customers into 3–7 distinct clusters. That range is deliberate: too few, and you lose nuance; too many, and the personas stop being practical—after all, personas power personalization and you don’t really want to customize 37 emails each time you make a send\! Remember, our AI is always powerful but is only value-driving when tied to a concrete business function.

The result: a persona set that reflects your business as it is today—and that you can use to personalize everything from top-of-funnel ads to post-purchase journeys.

## So how many persona sets do I need?

**In a nutshell, one is enough (we promise).**

Here’s the temptation (and we’ve heard it many times): you start to see interesting subgroups, and you think, “Should I just make a whole new persona set for my high-value customers? Or for leads? Or for gift buyers?”

But this is important: resist the urge. One persona set, built on your customer base (ideally recent customers), can answer all of those questions *if* you use it well. And what’s more, every additional persona set you create adds complexity—fragmented messaging, duplicated creative, messy reporting—with very little return.

Think about it practically. Let’s say you’re using personas to personalize emails. If you have 35 personas, you need 35 distinct emails each time you make a send, tailored to each persona. The same would be true for a direct mail campaign, or any other use case built on personas. 

And if you really want to dig into those subgroups, that is still a great option with one persona set, you just use **secondary analysis** instead of additional personas.

## Use secondary analysis for deeper insights

Let’s say you’re curious about your high-LTV buyers. Or people who tend to buy during promotions. Or those who give gifts.

The instinct might be to build a new persona set just for those customers—but that’s the wrong move.

Instead, use **secondary analysis** on the persona set you already have. This means identifying which of your existing personas are most likely to exhibit those behaviors. Does persona B have more high-value buyers? Does persona D respond more often to promotions? 

This lets you tailor messaging, promotions, or next-best-action logic *within* your current framework—without rebuilding the architecture from scratch.

You’re analyzing, not segmenting. That distinction matters. If your persona set is the architectural structure, secondary analysis is like putting sensors in each room to see who uses what, when, and why. It adds intelligence without requiring you to redraw the floorplan.

That’s why secondary analysis is the right tool for exploring behavior. It lets you get more specific without fragmenting your strategy.

## So would I ever use a second persona set?

We get this question a lot—and it’s not a bad one. In theory, there *are* situations where a second persona set could make sense. But in practice, they’re vanishingly rare.

Let’s say your business has two truly distinct models—like Netflix in the DVD-by-mail era vs. its streaming service. Maybe the customer base for each product barely overlaps. In a case like that, sure, there’s a logic to considering separate persona sets.

But even then, we don’t recommend starting there. First, build a single persona set from your full customer base and run secondary analysis. You may find that your personas naturally reflect the split without needing to manufacture two totally separate structures.

The risk of jumping too soon into multiple sets is high: fragmented messaging, duplicate effort, and confusing strategy. You’ve gone from one coherent framework to parallel tracks that require twice the upkeep—and often deliver half the clarity. 

**As Andy put it in a recent meeting:** 

**“If you really, really, really, really think you need more than one… you still don’t.”**

## How to use personas

Once you have a persona set built from your customers, the value comes from how you apply it.

You don’t just file it away as “interesting.” You use it as a structure to guide how you engage people across the entire funnel.

### Start with leads

Even though your personas were built on customer data, you can (and should) apply them to leads and prospects. Every lead can be mapped to the closest-matching persona based on their traits.

That lets you do smart things early—like showing persona-aligned Facebook ads, driving people to persona-specific landing pages, or customizing messaging tone based on emotional drivers. 

**As Andy says:**

**“You want continuity between how you handle leads and how you handle customers. That means the architecture has to start early.”** 

### Personalize campaigns

This is personalization 101\. Instead of blasting one-size-fits-all emails or ads, you vary your content based on what you know about each persona. Not to the point of infinite complexity—but enough to make the message feel more relevant, more human.

And you don’t need 37 personas to get there. Three to seven is plenty.

### Operationalize and scale

Personas are a strategic lens. They help you organize your audience, inform creative, and structure internal decision-making. In a large org, you could even assign brand managers to own each persona—getting deep into what makes that group tick.

Just don’t mistake them for a silver bullet. You’re not using personas to predict exact behaviors (like who’ll buy Product X on Thursday). For that, you’d use specific outcomes or predictive models. But for building audience structure and making smarter content decisions, personas are the starting point.

## Conclusion

If you take nothing else from this, remember this: your persona set is not a one-off project. It’s the structural framework—the architectural blueprint—that supports your entire customer engagement strategy.

When you get it right, everything else becomes easier. Ads align. Messaging resonates. Creative connects. And the decisions you make, from acquisition to retention, rest on a solid foundation.

Don’t overcomplicate it. Build once. Use often. And always start with the people who said yes.

Nearly every brand needs just one carefully built persona set—use secondary analysis, not additional sets, when you want more detail.

So how many persona sets do you need anyway?

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.