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 four categories: events, attributes, 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.|
|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.|
In this guide, we’ll provide an overview of Events data and discuss the various ways that it may be ingested into Cortex.
What are events?
An event is defined in Cortex as an action taken by a user (or any other type of object) at a particular point in time. Some examples of events include –
User XYZ logs in → User XYZ clicks on item ABC → User XYZ adds item ABC to cart → User XYZ purchases item ABC
Events form the basic building blocks of any Cortex pipeline, so it’s required that Events data be present in your account before you may begin building pipelines. At minimum, each event needs to contain the following three pieces of information:
- User ID: A unique identifier for the user that completed the event.
- Timestamp: Time at which the event was recorded.
- Type: Type of action that was taken (e.g. purchase).
Optionally, your events can also include any other information which paints a more detailed picture of the conditions under which the event occurred. The more info you include in your events, the wider the set of predictions you can make, and the more accurate your predictions will be. If you’d like to generate personalized item recommendations for each user, or if you are sending Items data into Cortex, your events must also contain an item ID indicating which item the user interacted with.
The below table shows what a sample of Events data might look like for an eCommerce company. Note that the data contains each of the three required fields, as well as two additional fields describing the user’s device, and the item that was interacted with.
Your events can reference more than one type of object (e.g. user and item), but each Cortex account can only be configured to make predictions about one or the other.
How do I send Events data into Cortex?
There are three ways that you can ingest Events data into Cortex:
1) Real-time APIs
Cortex offers a set of scalable APIs to stream live events into the platform right as they occur. These APIs can be deployed server-side or client-side (including integrations with Google Tag Manager and Tealium).
For details about how to send Events data into Cortex via real-time APIs, read the documentation for Vidora’s Behavioral API.
2) Batch File Uploads
Alternatively, you may transfer batches of Events data into Cortex by uploading files that you’ve exported from, say, your data lake or analytics 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.).
3) 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!