iCreatAI News
Skip to content
Trending storyWatching

Databricks releases real-time recommendation solution accelerator

1 reports1 sources1 days agoUpdated

Understand this story

AI overview

Databricks released an open-source Solution Accelerator that uses Feature Views to build a real-time next-best-offer recommendation system for the financial services industry, with the same feature definitions used for both training and online serving. The solution has two parts: a recommender based on batch features, and an extension that adds streaming in-session intent, both deployed end-to-end as runnable notebooks on Databricks. According to the Databricks blog, under a minimal configuration, streaming events become visible to the model in about 0.1 seconds. Everything runs on serverless compute governed by Unity Catalog; the second part additionally requires a Unity Catalog Kafka connection and Amazon MSK connectivity to bring in real-time session activity. Before use, you need a Databricks workspace, a configured Databricks CLI profile, and the accelerator's GitHub repository; after deploying the jobs, run the two parts in sequence and deploy the application.

AI overview based on source reports · Updated 1 days ago

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 17
  1. Databricks Blog
    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.

Activity for this story

Current comparable activity
4
Peak comparable activity
10Nov 17 03:00
Change in the past 24 hours
-51%

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.