Data storage
The customer data used for model training and inference remains in your data warehouse. We also store a cache of the customer data in the storage bucket configured in your Hightouch workspace.
This customer data includes:
- User features
- Outcome data (e.g. purchases, clicks, etc.)
- Recommendation data
For additional information on how Hightouch secures your data, refer to Hightouch's security documentation.
User features
User features are the user attributes that are used in the model training process. Eligible user features are whitelisted for model training in your Hightouch schema. These generally include:
- Demographic attributes
- Marketing engagement data (email clicks, SMS opens, etc.)
- Product interaction data
- User behavior data
User features do not include PII such as name, email, phone number, etc.
Model training and inference
Data usage for model training
User features and outcome datasets are used in-flight during the process of generating recommendations. The recommendation process is as follows:
- User features and outcomes are pulled temporarily into our execution environment
- The data is used to train a model specific to your data
- The model is used to generate recommendations
- The model and user data are not retained after inference in the Hightouch environment
Data sharing and privacy
All machine learning models produced by Hightouch are single-tenant and are not shared with other customers. They are used for the sole purpose of generating recommendations and are not retained after inference.
Customer data is also never shared with other customers for training or analytics purposes.