Marketing Personalization · Real-time Analytics
Burberry's daily clickstream batches arrived too late and its prior warehouse pre-aggregated the data, making it hard to trust granular customer-behavior details or personalize service for webrooming shoppers in time.
Reported impact
Burberry reduced clickstream latency by 99%, extended cookie duration 52x from one week to one year, improved marketing attribution and enabled store advisors to personalize service for webrooming customers while there was still time to influence the sale.
Burberry paired Snowplow's Behavioral Data Platform with the Databricks Data + AI Platform to replace slow daily clickstream batches from its prior warehouse with a near-real-time customer 360. Clickstream events from Burberry.com flow into Snowplow, where digital-touchpoint behavior is captured and privacy controls, consent tracking and server-side cookies are managed. The data then lands in Databricks, where 40 personalized models recalculate recommendations, propensity scores and lifetime value before sending outputs to the retailer's action system and in-store advisors. Burberry also uses the dbt plug-in for Databricks to enrich referral, consent-banner and server-side cookie data so marketing attribution reflects owned behavioral data instead of coarse pre-aggregations. This architecture lets store staff act on opted-in shoppers' most recent online behavior during the same webrooming journey.
Burberry.com clickstream events are captured by Snowplow and enriched with consent and server-side cookie data before moving into Databricks. There, 40 personalized models recalculate recommendations and scoring outputs, which are passed to the retailer's action system and surfaced to in-store advisors during the same customer journey.
After switching to server-side cookies with Snowplow, Burberry's cookies are now valid for 12 months.
As clickstream data flows in from Burberry.com, the company uses Snowplow BDP to realize real-time AI-Ready Customer 360s from across their digital touchpoints.
By implementing the Databricks Data + AI Platform and Snowplow's Behavioral Data Platform, Burberry formed a complete view of each customer (AI-Ready Customer 360).
From there, the data travels into the Databricks Data + AI Platform, which contains 40 personalized models covering tasks such as product recommendations, propensity scoring and lifetime value.
Our client advisors can pull out their iPad or iPhone devices to gain an instant view of what a customer really wants and which products to recommend.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Databricks Sample Sep 21, 2026 KakaoStyle KakaoStyle needed a more reliable and governed data foundation because fragmented infrastructure and data quality issues were slowing AI-powered search, recommendations, and commerce operations. Batch failure alerts for the data engineering team fell by approximately 90% after migrating to Databricks… Databricks Data + AI Platform · Genie · Lakeflow Databricks Sample Jun 12, 2025 Furniture.com Furniture.com is transforming online furniture shopping by unifying a fragmented industry with data and AI. 3.2x Increase in returning users with Find It AI Agent Bricks · Delta Lake · MLflow Databricks Sample Mar 26, 2025 ThredUp ThredUp needed a better way to support marketplace personalization, machine learning, and analyst self-service for fashion resale because marketplace scale and fragmented tooling kept onboarding slow and prevented… 71% to identify, train and stage ml models instead of weeks Databricks Data + AI Platform · Delta Lake · Genie 