---
title: "Real-Time Retail Intelligence: Building E-Commerce Recommendations with Lakebase and AI Search on Databricks"
description: "The post presents a reference architecture for building a production-grade e-commerce recommendation system on Databricks, based on a real-world implementation for a leading fashion e-commerce platform in Asia serving over 1 million monthly active users across 100,000+ SKUs. The system ingests approximately 1,000 events per second via Lakeflow Connect’s Zerobus into Unity Catalog Delta tables within a medallion architecture. Serving uses two paths: Path A for pre-computed batch recommendations via key-value lookup from Lakebase online tables, and Path B for real-time session-aware scoring using AI Search and a LightGBM model in a 3-stage funnel. The architecture unifies ingestion, feature management, model training, vector retrieval, and serving on a single governed platform, with cold-start handling for new users and products. Expected outcomes include low 2-digit millisecond responses, daily-fresh recommendations, and unified governance via Unity Catalog."
---

# Real-Time Retail Intelligence: Building E-Commerce Recommendations with Lakebase and AI Search on Databricks

[Databricks](https://yomu.fyi/company/databricks) · Sunny Singh · Oct 2, 2026

**Type:** Explainer

## Summary

The post presents a reference architecture for building a production-grade e-commerce recommendation system on Databricks, based on a real-world implementation for a leading fashion e-commerce platform in Asia serving over 1 million monthly active users across 100,000+ SKUs. The system ingests approximately 1,000 events per second via Lakeflow Connect’s Zerobus into Unity Catalog Delta tables within a medallion architecture. Serving uses two paths: Path A for pre-computed batch recommendations via key-value lookup from Lakebase online tables, and Path B for real-time session-aware scoring using AI Search and a LightGBM model in a 3-stage funnel. The architecture unifies ingestion, feature management, model training, vector retrieval, and serving on a single governed platform, with cold-start handling for new users and products. Expected outcomes include low 2-digit millisecond responses, daily-fresh recommendations, and unified governance via Unity Catalog.

## Context

Building a production-grade e-commerce recommendation system requires real-time data ingestion, complex feature engineering, multiple ML models, and low-latency serving, while keeping inventory and business rules in sync. This architecture addresses those challenges on a unified Databricks platform.

## Approach / What changed

The architecture uses Lakeflow Connect’s Zerobus for real-time ingestion into Unity Catalog Delta tables, a medallion architecture for data processing, Feature Store and Lakebase for feature management, AI Search for hybrid retrieval, LightGBM for scoring, and Model Serving for low-latency inference, with two serving paths: pre-computed batch and real-time session-aware.

## Takeaways

- The system uses two serving paths: Path A for pre-computed batch recommendations via key-value lookup from Lakebase online tables, and Path B for real-time session-aware scoring using AI Search and LightGBM in a 3-stage funnel.
- The architecture unifies ingestion, feature engineering, model training, vector retrieval, and serving on a single Databricks platform governed by Unity Catalog, eliminating the need for multiple specialized systems.
- Cold-start for new users is handled by generating an embedding from demographic and sign-up data, while new products inherit scores from similar existing items via attribute-based embeddings.

## FAQ

### How does the system handle real-time session signals during inference?

In-session user signals are sent directly as part of the API request payload to the Model Serving endpoint, bypassing lakehouse storage to avoid ingestion latency.

### What is the difference between Path A and Path B serving?

Path A serves pre-computed batch recommendations via key-value lookup from Lakebase online tables, while Path B performs real-time session-aware scoring using AI Search and a LightGBM model in a 3-stage funnel.

### How are new users and new products handled?

New users get an embedding from demographic and sign-up data for ANN search, while new products inherit scores from similar existing items via attribute-based embeddings.

**Tags:** [AI Search](https://yomu.fyi/topic/ai-search), [Databricks](https://yomu.fyi/topic/databricks), [E-commerce](https://yomu.fyi/topic/e-commerce), [Lakebase](https://yomu.fyi/topic/lakebase), [Recommendation Systems](https://yomu.fyi/topic/recommendation-systems)

- Source: [Databricks](https://www.databricks.com/blog/real-time-retail-intelligence-building-e-commerce-recommendations-lakebase-and-ai-search)
- Source URL: https://www.databricks.com/blog/real-time-retail-intelligence-building-e-commerce-recommendations-lakebase-and-ai-search
- Ingested by Yomu: 2026-10-02T12:00:08.474Z

[Read original post](https://www.databricks.com/blog/real-time-retail-intelligence-building-e-commerce-recommendations-lakebase-and-ai-search)