Databricks launches real-time next best offer system
The story so far
Databricks has launched a real-time next best offer (NBO) system via Feature Views, which consists of two parts: batch features and adding streaming session intent, both built on Databricks, and provides runnable notebooks that can be cloned. Stream events become model visible features in about one-tenth of a second, training and serving generate the same feature values to avoid bias. This accelerator is designed to build real-time NBO recommenders for the financial services industry.
AI-written from the reports · Updated 7 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- Databricks BlogDatabricks Feature Views build real-time next best recommendation systems
Databricks Feature Views eliminate logical redundancy between offline training and online serving through a unified definition of features, achieving real-time next best recommendation (NBO). This accelerator includes two parts: using batch features and extending streaming session intent, both built on Databricks and providing runnable notebooks that can be cloned. Stream events become model visible features in about one-tenth of a second, training and serving generate the same feature values, avoiding bias.
Heat over time
- Now
- 8
- Peak
- 1017 Nov, 03:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.