Changelog

This change improves percentiles and probabilities for scopes with outcome payloads by aggregating individual-level output at the residence and region levels.

The Market Opportunity Analysis (MOA) API endpoints and UI integration have been implemented within Pipeline pages, allowing users to create, manage, and archive MOAs directly through the platform.

View our documentation or API reference for more information.

This update introduces a new trait detail page in the Dashboard UI, making it easier for users to access trait analysis without digging into cohort creation. The page, located at /traits/ID, includes charts, general trait information, and a contribution card that highlights which datasets serve each trait—similar to the event streams detail page.

This change implements a Scope efficacy reporting module via a new API endpoint (accessed through GET /scopes/X/efficacy) and UI. This allows users to assess the efficacy of specific scopes through detailed reporting within the Dashboard.

These reports are similar to pre-sales holdout analysis but provide ongoing feedback to clients about the alignment between Faraday’s predictions and actual outcomes.

View our documentation to learn more.

Some accounts have numerous unused resources and archiving one by one is tedious if the numbers are high. This update allows users to select multiple rows on list pages to archive various resources at once.

In the API, an outcome’s performance can now be analyzed based on recognition level, which is broken down into all individuals (default), recognized individuals, and unrecognized individuals.

• all_individuals: includes all individuals, regardless of recognition level.
• recognized_individuals : individuals enriched with Faraday’s data
• unrecognized_individuals : individuals with client-data only (no enrichment)

The GET outcome analysis request will return the performance at each separate recognition level.

In the API, GET requests for cohorts will now return residence_count alongside the previously-available individual-count.

Each pipeline includes a diagnostics section that runs checks to help ensure that your pipelines are properly configured. These checks will look at both the population and payload of a pipeline, then compare them with the eligible population used in the predictions (outcomes or recommenders) themselves.

Check out our docs for full details.

Users can now provide a Webhook endpoint (via POST /webhook_endpoints) to receive real-time notifications about resource status changes in their account. This enhancement is particularly beneficial for our Powered by Faraday clients who rely on timely updates to orchestrate their Faraday configurations.

View our documentation to learn more.

Identified and referenced deployments will now include an enrichment precision column. This is broken down into individual-level and residence-level.

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

The Faraday Identity Graph received a significant update, with over 800 brand new traits and updates to hundreds of existing traits. These new and updates traits are available by default for users when building predictive models–no additional action is required. Check out our blog for more info.

Faraday now allows users to export the traits available to their accounts as a CSV. When cross-referenced with FIG, this export creates an up-to-date data dictionary, providing an overview of trait metadata such as category, coverage, and class.

View our documentation to learn more.

The events index in the Dashboard UI now displays the number of events in each event stream, when the most recent event was added, and the status of the event stream (e.g. ready, error). Additionally, each event stream now includes a section for analysis that shows the event stream's change over time.

Faraday's Lookup API now supports the use of identity sets, which enable you to include multiple identifiers in a single request, rather than having to create a separate request for each identifier. If the root identifier isn't found, Faraday searches for a match through each subsequent identifier. For more info, check out our Lookup docs.

Users can now automatically declare all columns in a Dataset as Traits, eliminating the need to manually label each one. This is achieved using the output_all_columns_as_traits property, which includes options to fine-tune which columns are included or excluded.

View our documentation to learn more.

Added three new date columns to resource index views. Created date is the date that the resource was created. Modified refers to the date that the resource’s configuration was last modified (e.g. a trait was added to a cohort’s definition). Lastly, processed is the last time the output was processed by Faraday (i.e. the output changed). Additionally, columns can now be sorted by ascending or descending values.

Added the ability to archive resources via the options menu on any resource. Attempting to archive a resource with downstream dependencies will result in a message stating that archiving this resource will also archive its dependencies. Resources that have been archived can be viewed via the archived filter on the list view of that resource type, and they can be unarchived via the same options menu.

Added a resource dependency visualization to each resource, which reveals the overall layout of resources in your Faraday account, and highlights which individual resources are connected to the one you’re currently viewing. This visualization can be helpful for understanding the impact that editing, deleting, or archiving a resource can have on your account.

Faraday now provides clients with explicit control over their models' use of 1st-party and 3rd-party data in their Pipelines. This allows clients to compare scores based exclusively on 1st-party data to those with a combined data set, featuring both 1st and 3rd-party data.

This update ensures more transparency and flexibility in data management, reducing manual intervention and increasing trust in the results.

The deployment card in a pipeline has received a facelift, and now only displays the most critical info by default: connection you’re deploying to, representation format (hashed, identified, etc), and any filters you’ve added (e.g. top 20%). Additional info can be found inside "more details."

Added the conditions option during dataset creation in the Dashboard UI or using the API via the create dataset request. Use this option to declare conditions that an event must meet in order to be considered an event. For example, if a dataset includes a field that classifies a transaction as cancelled, users can set a condition that requires the event’s cancelled field to be false, resulting in all cancelled transactions being filtered out of that event.

Terminology for enabling a pipeline has changed to a status called preview mode. All pipelines begin in preview mode, which includes a limited number of rows. This can be used to test if the output is in the desired format. To deploy all rows, simply turn off preview mode once you’ve created a deployment in the pipeline. This function is available via the preview parameter in the create scope and update scope API requests.

Individual persona names within a persona set can now be customized via the pencil icon when viewing a persona set in the Dashboard UI, or via the new edit a persona API request.

When creating an outcome, users now have the ability to disable their first-party data, resulting in an outcome created exclusively from the Faraday Identity Graph's third-party data. This can be helpful for performing holdout tests.

When creating or editing a dataset, the advanced options tab can be expanded to view the new privacy setting. Selecting "delete" excludes individuals matched in this dataset from being used for modeling, and removes them from all deployments. Selecting "exclude" continues to use individuals matched in this dataset for modeling, but excludes them from deployments. This feature can also be utilized via the new privacy parameter in the create dataset and update dataset API requests.

When creating a pipeline, users now have the ability to add raw traits to the payload. Adding traits to pipeline payloads in this way will append those trait values for every member of the pipeline's population.

Previously, a reference key needed to be set within a dataset, which enabled you to easily merge predictions back into wherever your data is stored. With this update, you can configure reference keys while creating a deployment.

Faraday's Lookup API now supports aggregated deployments when using the createTarget request with Lookup API set as the option parameter.

The new API shortcuts feature, accessible via the options dropdown (...) on most resource detail pages, allows you to retrieve API shortcuts in shell, Javascript, Python, and Ruby, so that you can easily transition from interactive configuration using the Dashboard UI to programmatic configuration with the API.

A new dataset type has been added—merge dataset—which allows you to merge two sets of data using a join key as an identifier. This type of advanced dataset can be useful if you have customer data in two different tables–for example, customers in one, and orders in another–and would like to combine them for more streamlined usage.

If an individual isn’t recognized at a particular address, Faraday now can still accurately enrich their data using the aggregate traits of others in the same household. This update extends our existing postcode-level aggregation to the address level, ensuring even better coverage for modeling.

Previously, when connecting your data to Faraday, individuals we didn’t recognize (those without a match in the Faraday Identity Graph, or FIG) were simply dropped from your data. Now, data about these unrecognized identities are ingested and stored normally. You can now review how your data is being enriched with FIG traits via the new enrichment column in Datasets. The higher the fill rate, the more identities we were able to enrich with our built-in consumer data.

These changes may result in larger cohort counts due to Faraday being better able to handle partially-matched identities. On the other hand, your pipelines that target the everyone cohort as a population to include may be smaller due to identity resolution improvements, where previously individuals may have been incorrectly counted twice. Overall, these changes should increase prediction accuracy.

Faraday’s UI now provides API shortcuts, allowing users to seamlessly transition from manual setup to programmatic workflows. Each resource’s three-dot menu includes a new "API Shortcuts" option, which opens a modal displaying pre-built API requests for that resource.

Faraday’s Outcome abstraction allows users to define propensity objectives which predict whether a person is likely to join a given Cohort (often, to experience a given event). In other cases, users want to determine which variant of a given event a person is likeliest to experience. For example, which product they are likely to buy next. This is what we call product recommendation.

A new POST /recommenders endpoint has been added to create recommenders, where you define parameters like stream name, eligibility, predictors, and bias mitigation.

View our documentation to learn more.

While creating an outcome, the bias section provides options for mitigating either of the two sensitive dimensions released at launch: age and gender. To mitigate bias, simply toggle on either (or both) age and gender, and choose a mitigation strategy from equality or equity. Equality aims to neutralize bias, whereas equity aims to invert it. For more info, check out our blog.

A new connection has been added for Secure File Transfer Protocol (SFTP), allowing users to securely transfer CSV data to and from Faraday.

Now, aggregated deployments in the UI can support census tract and block group zoom levels, which can be useful for canvassing & market sizing use cases.

Introducing a new look for the outcome performance dashboard to make it easier to interpret the results you can expect when using the outcome in the real world. In this new look, Faraday will place your outcome’s score on a grid whose Y axis is associated with Faraday’s ability to predict the outcome, and the X axis is associated with the business value expected due to the predictive lift of the outcome. The further toward the top right corner, the better your real-world results.

At the end of 2023, the Explore map will be deprecated due to low engagement and insights that are no longer as relevant as they once were.

With this update, you’ll find an include prediction explanations checkbox that tells you which datapoints had the highest impact on a given individual's predictions. Check out our blog post for more info.

When you create an outcome, the new bias section provides a summary of the bias that was discovered while the outcome was building. You’ll find tabs for different forms of bias–data, power, and predictions–as well as whether or not Faraday found the outcome to unfairly privilege certain sensitive subgroups over others. Click into any of the tabs to find the breakdown of given subgroups and their bias.

FIG is now able to update on an incremental basis, which should result in faster updates & more accurate predictions.

Users can now duplicate cohorts via the three dots on the cohort list view, or within the cohort itself.

When creating a dataset, you'll find previews of the data each of your properties represents while mapping fields. Similarly, when creating a cohort, you'll see a visual preview of the U.S. population baseline for Faraday traits that you add to the cohort.

Until now, the ability to filter a deployment by a percentile of scores existed in both the newer "filter" menu as well as the older "limit" menu. With this update, that option has been removed from "limit" to remove any confusion surrounding the redundant option. Users should continue to use the "filter" option and select "outcome percentile" to accomplish this task.

Faraday's Lookup API enables users to pull individual real-time insights via API.

The Outcomes view now includes various features that were previously stored in the technical model report, such as lift table and features of importance. The full technical model report can still be accessed via the three dots in the upper right when viewing an outcome.

Managed connections to your favorite martech platforms like HubSpot, Iterable, and Facebook are now easier than ever to use. If they're part of your subscription, head to Connections and enter your credentials.

Ever wondered what Faraday “scores” really represent? Starting now, we’re returning true probability values. That means that someone with a propensity score of 0.8 for a given Outcome truly has an 80% probability of achieving that Outcome. The calibration process we added also has the benefit of improving accuracy, which you will see by default in all new models. Check out our probability scores blog post for more details.

Now, when creating a deployment in Faraday, you can use the filter advanced settings pulldown (after selecting your deployment format) to select specific payload elements (personas, outcomes, and cohorts) to include in the deployment. This change includes moving the percentile filtering from the limit pulldown into this new filter pulldown. Limit will now exclusively be used to limit a deployment's row count.

For more info on how this new feature functions, check out our Pipelines documentation.

In a dataset's data tab, you are now able to download previously-uploaded CSVs so that you can compare them to new data that you'd like to upload to ensure that their columns match. This is accomplished via the three dots (...) to the right of the row.

Enable test mode via the toggle that appears when clicking your organization's name in the upper left. Enabling test mode saves all of your current data in Faraday and brings you to an instance of your account exclusively populated by artifical data, where you can test various features in sandbox mode. Use the same toggle to return to your regular Faraday account.

Find documentation for help getting started, full guides for Faraday prediction recipes from end-to-end, as well as walkthroughs for every part of Faraday.

When creating a deployment, in the advanced settings step's structure tab, you can select from various ad platforms such as Facebook, LinkedIn, Google Ads, and Pinterest to have the deployment automatically format in a way that's appropriate for that destination.

Places enables API users to designate points of interest around which they can focus predictions, and our new lead scoring quickstart guide details how you can quickly begin scoring leads in real-time using the developer API.

When creating a pipeline deployment, you're now able to select human friendly deployments, which changes column headers to the names of the outcome or persona set in use. This also includes full customization of column header names, if desired. These changes should make it easier to tell, at-a-glance, what each column header represents.

Clients will now need to have a direct contractual relationship with Liveramp, rather than using Faraday's Liveramp account. This is to better align Faraday with data processing best practices.

View all of your events and traits in their own consoles under the Data section of the navigation bar. The new traits console will serve as your in-app data dictionary, where you can search for what traits can be matched for and filtered by.

Reorganized the navigation bar into sections–Data, Predictions, and Account–to make navigating the app easier.

This update to Faraday’s predictive modeling means lead and customer engagement scores that evolve based on customer behavior, so interventions to save deals are more effective, improving conversion rates. This won’t be an option you select in the UI, but it should result in more accurate predictions.

With this enhancement, you’ll see columns for each payload element (outcomes, personas, cohorts) of a pipeline you’ve created–previously only outcomes were supplied.