This page lists a changelog of updates to Faraday.
- Dataset & cohort previews: 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.
- Cohort duplication: Users can now duplicate cohorts via the three dots on the cohort list view, or within the cohort itself.
- Faraday Lookup API: Faraday's Lookup API enables users to pull individual real-time insights via API.
- Deployment limits and filters: 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.
- Outcomes model reporting: 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: 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.
- Probability scoring: 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.
- Deployment filtering: 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.
- Refreshing datasets: 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.
- Test mode: 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.
- New product recipe and documentation: 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.
- Target transformation for ad platforms: 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.
- Human friendly deployments: 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.
- Developer API Places: 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.
- Liveramp partnership update: 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.
- Navigation bar update: Reorganized the navigation bar into sections–Data, Predictions, and Account–to make navigating the app easier.
- Events and Traits consoles: 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.
- Dynamic scoring: 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.
Aggregated pipelines: 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.
For example, if a persona set is included in your pipeline's payload, you can see the number of people in a given persona within your specified geographic level in the pipeline's deployment, when selected aggregated as the deployment type.