Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Databricks opens real-time banking offer recommender

AI summary

Databricks Blog published an open-source Solution Accelerator that uses Feature Views to build a next-best-offer recommender for retail banking. Its runnable notebooks combine batch features with a streaming extension for in-session intent, and the vendor reports 34 ms p95 ranking latency in its smallest benchmark configuration. Databricks says the ranking endpoint sustained about 56 requests per second and the Feature Serving endpoint about 390 requests per second before exceeding a 50 ms p95 latency threshold.

In-depth insight

The accelerator provides a practical reference implementation for reusing consistent feature definitions across model training and low-latency serving, though the published performance figures are vendor-reported.

Real-time personalization depends on understanding what customers want in the moment. When a retail banking customer checks their accounts, explores credit cards, or opens a loan calculator, each interaction signals their current intent. A relevant offer needs to reach them while they're still in the session.

The challenge is making that intent available to the model. Raw clickstream data must be aggregated into time-windowed features for two purposes: training on historical values as they existed at a given point in time, and serving predictions using current values with millisecond latency. Building these pipelines separately creates duplicate feature definitions that can drift over time and degrade model accuracy.

Databricks Feature Views solve this by letting you define features once for both training and serving. In this blog, we'll walk through an open-sourceSolution Accelerator that usesFeature Views to build a real-time next-best-offer (NBO) recommender for financial services.

Image 1

#Databricks#Databricks Feature Views#Databricks Model Serving#Databricks Feature Store#Unity Catalog#Apache Kafka#Amazon MSK#Delta Lake

Original · 8 min readRead the original
Group chat

No comments yet. Start the conversation.