Databricks explains real-time fraud detection with Feature Views
Overview
Databricks publishes a walkthrough of real-time fraud detection built on Feature Views in Databricks Feature Store.
The example follows a $900 payment from a Kafka stream to a fraud score served by Model Serving, with code at each step. According to the post, Feature Views let teams define each feature once and use that definition for both point-in-time training data and managed pipelines for online inference. The model combines five-minute transaction counts, a 30-day spending baseline and the current payment's details.
Written by AI from the articles below · updated Nov 6, 12:30 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Databricks BlogOfficialDatabricks explains real-time fraud detection with Feature Views
AIDatabricks walks through real-time fraud detection using Feature Views in Databricks Feature Store, following a $900 payment from a Kafka stream to a fraud score served by Model Serving. Feature Views let teams define each feature once, producing both point-in-time training data and managed pipelines for online inference. The model combines five-minute transaction counts, a 30-day spending baseline and current payment details.
Heat Trend
- Current comparable heat
- 6
- Peak comparable heat
- 6Nov 6, 1:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.