Cortex extends the value of your business’s unique data by enabling anyone to transform that data into Machine Learning Pipelines. The types of data supported by Cortex fall into five categories: events, attributes, subscriptions, items, and ID mappings.
|Events *||Timestamped actions taken by your users.||Customer ABC completes a purchase event at time T.|
|Attributes||Characteristics or traits of your users.||Customer ABC has job title ‘Professor’, and age 49.|
|Subscriptions||Records of which users subscribed to which offerings and when.||Customer ABC has subscription ‘Premium’ with start time T and end time null.|
|Items||Metadata attributes for the items that your users interact with, via events.||Item XYZ has category ‘shoes’, and price 49.99.|
|ID Mappings||Associations between one set of IDs and another.||Customer ABC has cookie ID 123.|
What are subscriptions?
Subscriptions provide information about the packages or offers to which your users are subscribed. Subscriptions are optional in Cortex, but recommended for businesses with a subscription model. Sending this information into Cortex makes it easier to create high-quality predictions about user acquisition, upsell, and churn.
Each subscription record must contain the following four pieces of information:
- User ID: A unique identifier for the user that completed the event.
- Tier: The name or ID of the subscription package to which the user is subscribed.
- Start Time: Time at which the subscription started. Supported formats include unix and ISO 8601.
- End Time: Time at which the subscription ended (if applicable). Supported formats include unix and ISO 8601.
The below table shows an example of what Subscription data might look like for a set of subscribers. Note that Cortex must be able to match each user’s subscription with their events, so please be sure to either (a) reference the same set of IDs, or (b) send a separate ID Mapping data source into Cortex.
How do I send Subscription data into Cortex?
If you are sending subscription and cancellation events that can be relied on as a source of truth, Cortex can automatically update your subscriptions table on an ongoing basis. However, a historical snapshot of your subscribers is still necessary to import into the platform. There are two ways that you can ingest subscriptions data into Cortex:
1) Batched File Uploads
Subscription data can be batch uploaded to Cortex in files exported from, say, your data lake or CDP vendor. To do this, schedule a recurring file upload into a cloud-based directory hosted by either you or Vidora. Cortex provides flexibility around both the format of these files (CSV, JSON, Parquet, etc.) as well as the type of directory into which they’re uploaded (Amazon S3, Google Cloud, Azure, etc.).
2) Direct Integrations
Vidora integrates with several third party platforms (CDPs, data warehouses, analytics providers, etc.) commonly used for enterprise data storage. For more information about the data source integrations supported by Cortex, click here.
Still have questions? Reach out to firstname.lastname@example.org for more info!