Key abstractions
The core resource types you build with in Faraday — connections, datasets, cohorts, predictions, pipelines, and deployments.
Faraday's key abstractions are the resource types you assemble to get context out of the platform: connections and datasets describe your data, events and traits give it meaning, cohorts define groups of people, outcomes and persona sets and recommenders make predictions about them, and pipelines and deployments send the results somewhere useful. Each page here defines one abstraction and how it depends on the others.
Accounts
Accounts are the fundamental container for your Faraday resources, defining data isolation and API access.
Atlases
Atlases are collections of geographic locations that let you filter people by proximity and attach each person's Nearest Location to a deployment.
Cohorts
Cohorts are groups of people that your business is interested in, such as customers and leads.
Connections
Connections are how you connect your data with Faraday, whether it's in a database, warehouse, cloud bucket, or somewhere else entirely.
Datasets
Datasets are how you describe your data to Faraday, accomplished through identity sets, events, and traits.
Data Appends
Customers can use data appends to enhance their internal datasets with rich third-party attributes. This information improves targeting, allows for better research, or even allows for them to enrich their own predictive models.
Deployments
Deployments (targets in the API) are created in pipelines, and are how you choose where your predictions should go and what they should look like.
Events
Events (streams in the API) show Faraday how to recognize actions taking place in your data, such as purchases, renewals, clicks, and more.
Forecasts
Coming soon, Forecasts will let you predict the value and frequency of transactions an individual will make over a certain timeframe.
Market Opportunity Analysis
Market Opportunity Analysis reports help you identify actionable growth opportunities in your market.
Outcomes
Outcomes are predictions that tell you how likely individuals are to take virtually any action, such as convert or churn.
Persona sets
Persona sets are predictions that organize your cohorts into thematic groups based on trait similarities to enable personalization insights.
Pipelines
Pipelines (scopes in the API) let you choose which predictions you want to deploy, who you want to make those predictions on, and where they should go.
Recommenders
Recommender predictions allow you to predict which product, service, or other offer that any individual is likely to respond best to.
Traits
Traits are interesting features about individuals and/or their households, sourced from both your data and Faraday's.