_This article is a followup to our [bias reporting](/blog/faraday-bias-reporting) article, and aims to provide a high-level overview of how Faraday users can mitigate harmful bias._

## What is bias mitigation in machine learning?

Bias mitigation in machine learning encompasses a set of methodologies and techniques devised to diminish and ideally eradicate unjust and discriminatory predictions inherent in the decision-making processes of artificial intelligence (AI) systems. This is a key component of [Responsible AI](/features/responsible-ai).

Bias, often unintentional, may infiltrate these systems as a result of the historical data they are shown, leading to inequitable treatment of specific demographic groups. For example, there is a history of [discrimination](https://www.investopedia.com/the-history-of-lending-discrimination-5076948) against specific minority groups in financial lending, and this history can perpetuate bias if it is not intentionally mitigated.

It is important to note that not all algorithmic bias is harmful. Predictions about, for example, the likelihood of buying products that are exclusively relevant to, say, certain age groups will and should discriminate in favor of those age groups. For the remainder of this article, when we discuss bias, we’re excluding innocuous bias like this and focusing on harmful bias.

Bias mitigation ensures that AI systems render decisions characterized by impartiality and fairness, irrespective of variables such as race, gender, or other sensitive attributes. This undertaking is pivotal in the development of AI systems that uphold principles of fairness and equality for all individuals.

The subsequent sections of this article describe how Faraday’s bias mitigation feature allows users to create fair propensity predictions. For more on bias management in Faraday, read our [bias management announcement](/blog/faraday-bias-management-announcement).

## How to reduce harmful bias in machine learning

When predicting propensity, Faraday can mitigate bias in two broad ways:

1. The first step is to ensure that the predictive algorithm considers every demographic group as equal. In order to do so, Faraday rebalances your historical data before submitting it to the algorithm for pattern discovery.
2. Second, when later making predictions, Faraday will adjust the nominal propensity ranking to ensure that the highest scorers for each demographic are ranked highly overall. This ensures that the predictions are meeting the fairness objective while maximizing predictive lift.

Some Faraday terminology will be used here, and will link to documentation.

### Unbiasing historical data

In order to mitigate bias in a client’s existing customer data, Faraday assigns different “weights” to each customer in the data to fine-tune their influence on the model's learning process. The goal is to address and rectify biases present in the data, ensuring that the model gives equal consideration to all relevant examples.

To understand this process, consider an example: a home mortgage company. Given historical disparities arising from discriminatory laws and government policies (among other reasons), some demographics are less likely to appear in the company’s customer data.

Formally, Faraday will discover this by noticing a difference between the “attainment” (all customers) and “eligible” (regional adult population) [cohorts](/docs/product/cohorts) in one or more dimensions of concern. For example, we could find fewer women than men in the historical customer data, even though the regional population is an even split: a disparity that has no rational basis. Without correction, the algorithm would believe (incorrectly) that there is some intrinsic quality which makes men more likely mortgage customers than women.

To unbias the historical data, Faraday would give higher weights to customers in underrepresented or disadvantaged groups, increasing their influence on the algorithm while it is looking for salient patterns. Building on the mortgage example above, Faraday could give higher weight to the proportionally fewer women customers, evening out their influence versus men. This results in more equitable predictions for individuals belonging to these groups.

By adjusting the weights assigned to different customers, Faraday aims to create a more balanced and fair learning process, ultimately leading to AI models that provide fairer outcomes across diverse demographic groups.

### Unbiasing predictions

When you include a propensity [outcome](/docs/product/outcomes) in your [pipeline](/docs/product/pipelines), Faraday can take additional measures to rectify potential biases in the resulting predictions. After the initial predictions are made, this approach evaluates and adjusts them to ensure fairness and reduce discriminatory outcomes.

Given that the first step eliminates bias in the historical customer data, why is this second step even necessary? When we unbias historical data, we can't alter the algorithm to completely ignore the overrepresented population in favor of the underrepresented one–we’re simply telling it to pay more attention to the latter until it has a roughly equal representation. This weighting can have a cascading effect that creates biases of its own, though.

To take the mortgage example even further, maybe the women customers tend to be older than the non-customers, whereas the men customers tend to be younger than their non-customer counterparts–after the weight adjustment, this can make the trait _age_ mean that an individual is more likely to attain the outcome if they are older, unfairly penalizing those without that characteristic, which is why this step is crucial.

In this step, Faraday looks for differences between the demographic makeup of the pipeline’s eligible population and the subgroup receiving the highest scores. The predictions are then adjusted to align more closely with the desired fairness objectives.

This method allows for the correction of biases that may have been present in the original predictions, promoting a more fair distribution of outcomes across different demographic groups. By incorporating fairness considerations after the initial predictions are generated, prediction this re-ranking contributes to developing machine learning models that exhibit improved fairness and reduced problematic disparity in their decision-making processes.

## Mitigating harmful bias with Faraday

As of the publication of this article (February 2024), Faraday currently allows for bias detection and mitigation for the **age** and **gender** dimensions (these features are often referred to as protected classes or Dimensions Of Concern).

When you define a propensity outcome in Faraday, you can choose how you want the system to handle bias:

- **No mitigation**: The outcome fairness is only reported as part of the outcome dashboard. No further transformation is applied to ensure that protected classes are treated fairly. This is perfectly appropriate in cases where the product or service being sold is intrinsically linked to certain demographic groups.
- **Equality**: This mitigation strategy ensures that demographic patterns are similar between the eligible population and the target group (those with the highest scores). For example if “young adult, women” represent 25% of your eligible population, we ensure that any population targeted from the pipeline will contain 25% of “young adult, women”.

  The chart below depicts the effects of historical data bias mitigation using the “equality” setting with three populations (A, B, C). Population **A is underrepresented** in the customer data (attainment population)—30% are customers vs. 47% in the overall population while **B** and **C are both overrepresented**. The mitigation process ensures that in the target group, population **A** accounts for 47% while **B** and **C** account for their original 14% and 39% respectively.

  [![Equality bias mitigation](/images/blog/faraday_bias_mitigation/equality-mitigation.png)](/images/blog/faraday_bias_mitigation/equality-mitigation.png)

- **Equity**: This mitigation strategy “inverts” bias so that populations that were historically underrepresented are now instead prioritized.

  In the example below, the customer group (attainment cohort) consists of 30% of population **A**, 20% of population **B**, and 50% of population **C**. The equity mitigation is going to promote the underrepresented populations **A** and **B** at the expense of population **C**. The target population will contain 37% of **A**, 47% of **B**, and 16% of **C**.

  [![Equity bias mitigation](/images/blog/faraday_bias_mitigation/equity-mitigation.png)](/images/blog/faraday_bias_mitigation/equity-mitigation.png)

Note that when mitigating bias, Faraday will consider all dimensions simultaneously, leading the system to consider subpopulations like “young adult, women” and “middle-aged men.”

## Does mitigating bias hurt performance?

Because the bias mitigation process necessarily alters the ranking and promotes sub-populations with otherwise lower predicted scores, it can reduce lift.

That said, the impact is often small. The top two graphs below depict the impact of **equality** mitigation on Gender. The lift curve for the un-mitigated model is only slightly better than the one for the mitigated model. The main difference lies in the 20% to 40% score percentile range with lift in that range decreasing from ~300% to ~220%.

The two bottom graphs show the mitigation at work. On the left, the un-mitigated model will create a target group with 2x too many males.

After mitigation, the graph on the right shows only a slight discrepancy between the fair proportion of each gender, within 3%. This is a significant fairness improvement over the initial target population breakdown with only a minor reduction in performance.

[![Bias mitigation comparison](/images/blog/faraday_bias_mitigation/mitigation-comparison.png)](/images/blog/faraday_bias_mitigation/mitigation-comparison.png)

## Why mitigate bias?

Bias isn’t inherently harmful. Earlier in this article, we touched on innocuous bias that occurs when products or services are explicitly designed for and marketed toward certain groups, like a womens’ swimwear brand marketing mostly to women. It’s the _other_, harmful–and often hidden–bias that should be surfaced and mitigated.

With Faraday, bias mitigation is easy. If you find that a predictive outcome you created has bias that you want to mitigate, simply create a new outcome using the same cohorts of people, toggle mitigation on for the sensitive dimension in question, select your mitigation strategy, and save the outcome. Once it finishes building, compare the bias report from the un-mitigated outcome with the report from the mitigated outcome. Alternatively, use the **bias_mitigation** object with the API call to [create](/developers/reference/createoutcome) an outcome.

[![Bias mitigation comparison](/images/blog/faraday_bias_mitigation/bias-mitigation-in-app.png)](/images/blog/faraday_bias_mitigation/bias-mitigation-in-app.png)

It’s in the best interest of anyone developing or using AI to do so responsibly. Whether you’re using [generative AI](https://www.bloomberg.com/graphics/2023-generative-ai-bias/) for email copy and creative, predicting customer behavior like we walked through in this article, or something else entirely, you should be wary of the existence of bias in the data that the algorithms are using, and how it impacts who you market and sell to. By employing responsible, [explainable AI](/blog/what-is-explainable-ai-why-is-it-important), you can build a foundation of trust between not only yourself and your customers, but between your business and your data.

Responsible AI isn't just good business–it’s the right thing to do.

Mitigating harmful bias with Faraday is simple, whether through our developer API or in-app. Learn more about how Faraday mitigates bias in your customer predictions.

How Faraday helps mitigate harmful bias in machine learning

With increased expectations to provide meaningful customer experiences—and shrinking budgets—brands are looking for smart engagement techniques that use the tools they already know, love, and pay for. Join our team of experts from Faraday, Google, and Hightouch as we delve into the world of predictive customer engagement, offering insights on how you can elevate your strategy with your existing stack.

**In this session you’ll:**

- Uncover the potential of predictive models like propensity, spend forecasting, next-offer recommendations, and personas in enhancing and personalizing your customer engagement strategy.
- Gain valuable insights into the mechanics behind crafting precise predictions.
- Learn practical strategies for seamlessly deploying insights into your customer engagement tools.

With increased expectations to provide meaningful customer experiences—and shrinking budgets—brands are looking for smart engagement techniques that use the tools they already know, love, and pay for.

How to unlock data-driven customer engagement with predictive AI

Quantifying bias in predictive models is the first step towards building models with fair treatment of protected groups.

Faraday bias reporting: How we measure & report on bias

One of Faraday’s founding pillars is the use of [Responsible AI](/features/responsible-ai), which includes both preventing direct harmful bias and reporting on possible indirect bias. We’ve been building these features directly into the platform over the past several months, and today we’re going to walk through two new features in Faraday with **bias reporting** and **bias mitigation**.

## Bias reporting

To see the bias report on an outcome, head to [outcomes](https://app.faraday.ai/outcomes) and scroll down to the **bias** section to see the breakdown of bias discovered in the _data_, _power_, _predictions_, and _fairness_ categories, which we'll dive into below. These can also be retrieved via the API using [get outcome analysis](/developers/reference/getoutcomeanalysis).

[![Bias reporting on an outcome](/images/blog/faraday_bias_reporting/outcomes-bias-reporting.png)](/images/blog/faraday_bias_reporting/outcomes-bias-reporting.png)

Faraday uses four categories to report on bias for an outcome:

- **Data**: Measures selection bias in the underlying cohorts used in the outcome. In a Faraday outcome, two labels exist for the purpose of this blog post: _positive_, or the people from the attainment cohort that were previously also in the eligibility cohort, and _candidate_, or the people from the eligibility cohort.
- **Power**: Measures outcome performance on a subpopulation compared to baseline performance–for example, Faraday will compare how well the outcome performs on the subpopulation “Senior, Male” compared to everyone else.
- **Predictions**: Measures proportions of subpopulations being targeted compared to baseline proportions in order to see if the subpopulation is over or under-represented.
- **Fairness**: Measures overall fairness using a variety of common fairness metrics in the literature. For example, Faraday will look at whether or not the subpopulation "Senior Male" is privileged or underprivileged.

Each bias category uses groups of people called subpopulations, which are combinations of people defined in the [understanding bias reporting](/docs/product/outcomes#understanding-bias-reporting) section's **sensitive dimensions** dropdown table. Examples of these are "Teens with gender unknown" and "Senior Females." We're launching with two of these sensitive dimensions in **age** and **gender**, but will be rolling out more over time.

If you discover that one of your outcomes includes harmful bias, you can create a new outcome using the same cohorts, but enable bias mitigation options while creating it to compare results.

## Bias mitigation

When creating a new outcome, you can choose to mitigate bias by using the toggles in the **bias** section. Check out our [outcomes documentation](/docs/product/outcomes#mitigating-bias) for info on different bias mitigation strategies.

[![Bias mitigation in an outcome](/images/blog/faraday_bias_reporting/outcomes-bias-mitigation.png)](/images/blog/faraday_bias_reporting/outcomes-bias-mitigation.png)

<Callout type="warning" title="Taking action on bias">
Mitigating bias isn't something you should set-and-forget, meaning it's not recommended that you toggle both **age** and **gender** on for every single outcome you create. For example, if you're a womens' swimwear brand, your data will skew heavily toward women, and mitigating gender would negatively impact your lift.
</Callout>

Always keep the populations that you're making predictions on in mind when considering bias. In the above example, it's _totally_ fine to ignore the biased skew towards a certain gender or age group because they're your ideal customers.

We're thrilled to continue to drive Responsible AI forward by providing agency for our users to both discover and mitigate bias in their customer predictions. Stay tuned for a deep dive into the science behind how Faraday determines bias.

Learn how Faraday's bias management suite enables you to analyze and mitigate bias found in your customer predictions.

Introducing Faraday bias management

I've always loved Zapier. It really does feel like a superpower to set up a workflow with a zap: the gift that keeps on giving. This section has been on their homepage longer than anything else and I can see why — Zapier users all feel this way.

[![Testimonials from Zapier users](/images/blog/zapier/testimonials.png)](/images/blog/zapier/testimonials.png)

That's why I'm so excited and proud to share that you can now [incorporate Faraday predictions into your zaps](https://zapier.com/apps/faraday/integrations). With this new integration, you can score leads, assign customers to personas, make product recommendations to shoppers, forecast spend, and more, all within your automated Zapier workflows.

Predictions are the key to improving customer engagement throughout the lifecycle—you can personalize outreach, customize offers, prioritize better opportunities—the list goes on.

## Working through an example Zap with Faraday predictions

Let's say we want to score new leads when they arrive in HubSpot, evaluating them for their likelihood to close and assigning them to a persona. This way, you'll be able to tailor your handling of these leads differently according to their predictions.

### Faraday setup

We'll assume you already have basic customer and lead data, along with their respective cohorts, set up in your Faraday account. If you're new to Faraday, check out the [docs](/docs/intro/welcome) and [Faraday Academy](/docs/academy) to get up to speed.

Next, you'll need to set up your two predictions if you don't have them already:

1. **Lead scoring outcome** — [recipe](https://app.faraday.ai/recipes/lead_scores_in_lookup_api) or [docs](/docs/how-to/predictions/likelihood-to-convert)
2. **Customer personas** — [recipe](https://app.faraday.ai/recipes/persona_assignments_in_lookup_api) or [docs](/docs/how-to/predictions/customer-personas)

Finally, if you don't already have it, create a pipeline to get these predictions deployed:

- **Population** – everybody
- **Payload** – the two predictions above
- **Deployment** – Lookup API

That last bullet is important to get things working right on Zapier.

### Creating your zap with Zapier

I love Zapier's new LLM interface for creating zaps, and it works great here. Just head to your dashboard and type "When a new lead comes into HubSpot, score it using Faraday," like so:

[![Zapier prompt saying "When a new lead comes into HubSpot, score it using Faraday"](/images/blog/zapier/prompt.png)](/images/blog/zapier/prompt.png)

Zapier should automatically calculate your zap template for you—something like this:

[![Zapier template for "Score new leads in HubSpot with Faraday"](/images/blog/zapier/template.png)](/images/blog/zapier/template.png)

Hit that "Try it" button. This should load the template up in the zap editor, which will look something like this:

[![Zapier zap editor for "Score new leads in HubSpot with Faraday"](/images/blog/zapier/editor.png)](/images/blog/zapier/editor.png)

Click the HubSpot box to pull up settings for this trigger step. You'll have to choose your HubSpot account and then pick your lead capture form from the dropdown. It will look like this:

[![Zapier HubSpot settings for "Score new leads in HubSpot with Faraday"](/images/blog/zapier/hubspot.png)](/images/blog/zapier/hubspot.png)

Hit the test button, and it will find a recent lead from your form data. When you hit continue, you'll make your way into the Faraday action step settings.

Choose or add your Faraday account (you'll need your Faraday API key for this), then proceed to the Action section. In the "Select pipeline" dropdown, choose the pipeline you created earlier. If it's not on the list, make sure your Lookup API deployment was properly added to this pipeline in Faraday.

Then, use the form data from HubSpot to fill out as many of the identity fields as you can. In this case, we capture email in our lead form, so I'm using that (actually, the Zapier LLM had that preconfigured for me ✨):

[![Zapier Faraday settings for "Score new leads in HubSpot with Faraday"](/images/blog/zapier/faraday.png)](/images/blog/zapier/faraday.png)

After testing what you've got so far, it's time to store your predictions for this new lead somewhere. You could put them back in HubSpot with an "Update Contact" action, or whatever you'd like. Then publish your zap and you're all set!

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

Zapier is everybody's favorite workflow automation tool. Now, you can retreive predictions from Faraday in your Zaps.

Launch: Faraday predictions now in Zapier

AI is on everyone’s minds due to its myriad use cases and applications across industries. From chatbots getting people where they want to be faster, to providing [financial planning advice](https://quickbooks.intuit.com/au/blog/accountants-and-bookkeepers/accounting-ai/), to using ChatGPT to help out with a resume or piece of code, to making [customer predictions](/features/predictions) for likelihood to take an action and personalization–AI isn’t going anywhere anytime soon.

[64% of businesses](https://www.forbes.com/advisor/business/ai-statistics) feel that various aspects of their organization will see increased productivity due to AI, and it’s no surprise when you think about the countless tasks that people have been doing for ages–segmentation, data analysis, and so on–and how much time & effort is saved by offloading them to AI. The use of AI for generating content in particular has scaled so fast that discussions abound on the impact that this AI revolution can and will have on human jobs, and brands like [NPR](https://www.npr.org/2023/06/07/1180768459/how-to-identify-ai-generated-deepfake-images) and [MIT](https://www.technologyreview.com/2022/12/19/1065596/how-to-spot-ai-generated-text/) are publishing guides for how to spot AI-generated content.

## The black box problem

The issue at the heart of this AI quandary is known as the [black box problem](https://umdearborn.edu/news/ais-mysterious-black-box-problem-explained). In short, the problem is that while what we’re seeing AI accomplish is incredible–and seemingly accurate in many ways, at first glance–by and large, we don’t understand how it reaches its particular conclusions, and what data it uses to reach them.

Faraday has long pursued making AI that uses [responsible data](/features/responsible-ai) to make responsible predictions accessible for all, and part of this pursuit has been tackling the black box problem. Starting today, every customer propensity prediction made using Faraday infrastructure can include _explainability metadata_.

## Explainable AI now in Faraday

[![Image of explainability checkbox in Faraday](/images/blog/product/explainability/explainability-checkbox.png)](/images/blog/product/explainability/explainability-checkbox.png)

Sounds good, but what does this mean?

Faraday has always provided detailed technical reports that analyze the impact of key data points on predictions at the overall level.

Now, each prediction, down to the individual level, has its score explained by the features in your data that had the highest impact on that individual’s prediction.

[![Image of a Faraday outcome feature importance for number of children and age](/images/blog/product/explainability/explainability-features.png)](/images/blog/product/explainability/explainability-features.png)

In the above example outcome, we see that, overall, the **approximate number of children** and **age** are the most predictive factors. And we can see what ranges lead to what average impact. For example, people with no kids have—all else equal—a slightly higher probability than those with 1–2 kids. This kind of aggregate reporting has always been available in Faraday.

[![Image of a Faraday score explainability output](/images/blog/product/explainability/explainability-output.png)](/images/blog/product/explainability/explainability-output.png)

Above, we see an example of CSV output from a pipeline. John is impacted by this outcome’s major factors, age and number of children, and leaves him with a low probability.

Jane, on the other hand, exhibits a more unusual combination of traits that give her a much higher probability for different reasons. For Jane, both her household income and millennial lifestyle saw her conversion probability higher than John because this business often sees conversions from people with those traits–even if they’re not the dominant traits.

## Explainable AI is Responsible AI

The central idea of Responsible AI is to understand our models—how they work, why they produce the results they do—enough to identify and correct their shortcomings. That’s why we have invested so heavily in, for example, bias detection and mitigation here at Faraday.

But even as we develop a strong understanding of and confidence in our models in the aggregate, we must not lose sight of the impact that prediction can have on individuals. We should demand nothing less from our AI models than that they explain themselves. Explainability is as core to Responsible AI as transparency and fairness.

A simple statement that explains a given prediction may not seem like much at first glance, but we feel otherwise. The _just trust us_ hand-wave that has been the motto engraved on the black box around AI for decades has been preventing our industry from moving forward with respect and responsibility for businesses and people alike–until now. Now you can see exactly what data helped AI reach the conclusion that it did, and feel confident that you’re making responsible predictions with responsible data.

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

Learn how every individual you make customer predictions on had their score calculated.

Removing the black box around customer predictions with Faraday score explainability

Traditional approaches to personalization and customer engagement often miss the mark in understanding the constantly evolving preferences and behaviors of individual customers. In this webinar we'll explore how predictive AI can transform [personalization](/blog/predictive-personalization-machine-learning) and engagement to deliver relevant and timely interactions.

Join Directors of Accounts Alex Noyes and Nick Haggerty, as well as Director of Marketing, Perry McDermott as they discuss how predictive AI can transform personalization and engagement to deliver relevant and timely interactions.

**From this workshop, you'll learn**:

- How machine learning can be used to improve and scale personalization efforts.
- Why first-party and third-party data are crucial for personalization at scale.
- How to use product-level predictions to personalize offers and increase LTV.

Join Directors of Accounts Alex Noyes and Nick Haggerty, as well as Director of Marketing, Perry McDermott as they discuss how predictive AI can transform personalization and engagement to deliver relevant and timely interactions.

Delivering personalized experiences at scale with predictive AI

As brands expand their usage of machine learning for customer acquisition and engagement, there are two essential concepts that stakeholders should understand: [propensity and probability](/blog/propensity-vs-probability-predictions). In this workshop, we’ll dive into the core differences between these concepts and explore how they can impact decision-making and campaign performance.

Join Directors of Accounts Alex Noyes and Nick Haggerty, as well as Director of Marketing, Perry McDermott and Senior Data Scientist, Thibault Dody as they discuss real applications for probability scores.

**From this workshop, you'll learn**:

- What’s the difference between a raw propensity score and predicted probability?
- How can predicted probabilities improve engagement & retention strategies?
- When should probability be used over raw scores for different channels and targeting strategies?

Join Directors of Accounts Alex Noyes and Nick Haggerty, as well as Director of Marketing, Perry McDermott and Senior Data Scientist, Thibault Dody as they discuss real applications for probability scores.

Unleashing the power of machine learning with actionable probability predictions

Acculynx is an industry-leading software platform that helps roofing contractors grow and operate their businesses. Join Acculynx’s VP of Product, Mark Rattin, and Faraday's Director of Developer Solutions, Dave Small, in this webinar as they guide you through the development process of Acculynx's newly launched Lead Intelligence feature, powered by Faraday, which enables their users to accurately predict how [likely their leads are to convert](/predict/category/lead_scores).

**From this webinar, you'll learn**:

- When should you add machine learning to your product roadmap?
- What should you buy and what should you build?
- How Acculynx uses Faraday’s prediction API to power their Lead Intelligence feature

Join Faraday's David Small and AccuLynx's Mark Rattin for an insightful joint webinar that explores how you can harness Faraday's API for business growth.

Building predictive features that add meaningful value for customers

It’s no secret that [personalized direct mail](/blog/personalized-direct-mail-strategy) marketing is a great way to engage with your customers. Whether you’re interested in driving [repeat purchases](/predict/category/repeat_purchasers) from current customers, [finding new ones](/predict/category/likely_buyers), winning back old ones, or something else entirely, direct mail has proven to be an [increasingly effective strategy](https://www.postgrid.com/direct-mail-statistics/) to make your brand stand out in an era awash with the same old email marketing tactics. In this feature guide, we’ll walk through how to use Faraday to enable direct mail marketing campaigns that are highly personalized, and highly effective.

## How can Faraday be used for direct mail?

Faraday can be used for your direct mail campaigns by creating targeted cohorts, or groups of people, based on attributes from the Faraday Identity Graph, such as their ability to receive mail via, as well as their physical address. In this guide, we'll walk through how to **create a cohort** for direct mail, and how to use it when **deploying a pipeline**.

## Creating a cohort for mailable U.S. customers

To create a new cohort:

1. Navigate to cohorts via the menu bar on the left-hand side and click **+ New cohort** in the upper right.

2. Optionally, select an **event** for the cohort. In this specific direct mail use case, we're going to skip this step. For more info on this, check out our [cohorts documentation](/docs/abstractions/cohorts).

3. Next, click the **Add trait** button, which is the most important part in designating that this cohort of people are able to receive your direct mail.

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

4. In the **Add trait** popup, we're going to find & select the following trait:

- **Record quality code**: To ensure that the residence can receive mail at all. Choose the option to "select exact values from list" to select mailable.

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

<Callout type="info" title="Restricting by geography">

Optionally, add a _geography_ trait such as Postal code/ZIP to target specific locations. When using a cohort with a geographic restriction, like "Direct mailers in Burlington, VT," in a pipeline, the deployment will only include people in that locations.

</Callout>

5. Enter a unique name for the cohort, like _Direct mailers_, and click **Create cohort**.
6. Once finished, click **Save changes**. The cohort will begin building and will display with a _calculating_ message.

## Creating a pipeline to predict likely buyers for direct mail

While our _Direct mailers_ cohort is building (if we select it in a pipeline, the pipeline will build once the cohort is ready), we're ready to create a pipeline and deploy it via CSV, which will let us plug our direct mail cohort right into our preferred mailer platform. For a more detailed look at creating a pipeline, check out the [pipelines documentation](/docs/abstractions/pipelines).

1. Navigate to [Pipelines](https://app.faraday.ai/pipelines), and click **+ New Pipeline** in the top right to create a new pipeline.

2. In **population to include**, we'll grab the cohort we just created, _Direct mailers_, as we're only interested in the group of people we've selected: people in the U.S. who are able to receive direct mail.

3. In **population to exclude**, we can optionally add our _Customers_ cohort if we’re only looking for net-new customers.

4. For our **payload**, we'll select:

   - Our **propensity** (likely to buy) outcome. This should be a standard likely buyers outcome, with your _Customers_ cohort as the attainment, and _Anyone in Faraday’s identity graph_ as the eligibility. For more info on creating that outcome, see the [outcomes documentation](/docs/abstractions/outcomes). We’ll filter this outcome a little further on to target the top 20% most likely to buy people in this payload so that we're saving resources by not sending our direct mailer to people who aren't likely to buy.

   - Optionally, we can apply our **customer personas** to the people in this pipeline so that we can tailor creative & copy to their wants & needs.

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

5. Enter a unique **name**, and click **Save pipeline**. The pipeline will begin building, as indicated by a loading bar. You'll receive an email when the pipeline has finished building.

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

6. Once the pipeline is complete, head to the **Deployment** section inside the pipeline, and select **+ Add** under **Hosted CSV**.

7. We're presented with the choice of _Hashed, Referenced, Identified_, and _Aggregated_ as options for our predictions. Since we're creating a direct mail pipeline, select _Identified_ so that identities are not hashed, and we can see physical address information, and so we can filter by residence below.

   - In **Individual identification options**, we'll select _One row per residence (address)_ so that we don’t send mail to more than one person in a household.

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

8. Select **human friendly** for column headers that are easily readable, and click next.

9. Now we’ll expand **filter**, then click **add payload filter** so that we can specify that we’re only interested in the top 20% of likely buyers, ensuring we’re not wasting time and money on bad fits.
   - In the payload filter, select **propensity to buy - outcome percentile** to sort by score percentile, or the distributions of propensity scores within the _Direct mailers_ cohort we targeted.
   - Change the operator to **greater than or equal to (>=)** and type **81** into the next field. Since the scoring is inclusive, this means that, in this deployment, we’ll filter it in a way that we only receive the scores for the top 20% of likely buyers.

[![Faraday direct mail pipeline deployment](/images/blog/direct_mail_guide/direct-mail-guide-deployment-filter.png)](/images/blog/direct_mail_guide/direct-mail-guide-deployment-filter.png)

<Callout type="info" title="Filtering deployments">

If you have a specific budget to stay under, expand the **limit** option to add a cap on the number of rows you receive. For example, maybe each direct mailer costs \$10, and you have a budget of \$50,000. You’d set the limit to the top 5,000 rows.

</Callout>

10. Last, click **finish** to complete the deployment, after which it will begin building. We can use the download button to download the CSV of a completed deployment for upload into our direct mail platform, which will include the top 20% of likely buyers that are able to receive mail in the country, (optionally) with their predictive personas included so that we can tailor copy & creative appropriately.

[![Faraday direct mail pipeline deployment download](/images/blog/direct_mail_guide/direct-mail-guide-deployment-download.png)](/images/blog/direct_mail_guide/direct-mail-guide-deployment-download.png)

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

How to use each feature in Faraday to create predictions that enable you to accurately target direct mail campaigns through propensity predictions.