Build a real-time next-best-offer recommender using Databricks Feature Views
Build a real-time next-best-offer recommender using Databricks Feature Views
Databricks describes an open-source Solution Accelerator that uses Feature Views to build a real-time next-best-offer recommender for retail banking, defining batch and streaming features once for both point-in-time-correct training and low-latency serving. The accelerator combines a LightGBM ranker trained via the Feature Engineering SDK with a route-optimized Model Serving endpoint that scores 40 offers per request, and in its smallest benchmark configuration ranking requests fit within a 50 ms budget while streaming events became model-visible in about a tenth of a second. The post notes the accelerator uses synthetic data and demonstrates infrastructure rather than proven revenue uplift, and that eligibility, consent, suitability and suppression controls must be implemented before production.
Source: Databricks Blog · databricks.com