AI-powered personalisation at massive scale

Saks Fifth Avenue uses SurrealDB's vector search and graph capabilities to deliver real-time, AI-powered personalisation across 5 million luxury customers and 45 million monthly product-recommendation queries.

IndustryLuxury Retail

Revenue$6 Billion annually

Scale5M+ customers

Queries45M+ monthly

01 |KEY CHALLENGES

What they needed to solve

The technical and operational hurdles the team faced before adopting SurrealDB.

Massive scale requirements

Processing 45 million recommendation queries monthly for 5 million customers required unprecedented database performance and scalability.

Low conversion rates

Despite significant web traffic, conversion rates were stagnant at 1.5%, far below industry benchmarks for luxury retail.

Real-time personalisation

Generic product recommendations led to disengaged customers. They needed millisecond response times for personalised suggestions.

Complex data relationships

Customer preferences, purchase history, browsing patterns, and product relationships were spread across siloed systems, making unified analysis impossible.

02 |SOLUTIONS

How SurrealDB helped

The architecture decisions and SurrealDB capabilities that addressed each challenge.

Massive-scale vector search

Implemented SurrealDB's vector search capabilities to process 45 million recommendation queries monthly with sub-100ms response times, enabling real-time AI-powered personalisation.

Graph-based customer intelligence

Leveraged SurrealDB's graph database features to map complex relationships between 5 million customers, their purchase history, browsing patterns, and product preferences.

Unified data platform

Consolidated customer data from multiple touchpoints into a single, scalable platform, eliminating data silos and enabling comprehensive customer insights.

AI-enhanced recommendation engine

Integrated large language models (LLMs) with SurrealDB's vector capabilities to deliver contextually aware, personalised product recommendations that adapt to customer behaviour in real-time.

03 |RESULTS

The impact

Measurable outcomes delivered after moving to SurrealDB.

45M

queries

Massive scale achieved

Successfully processes 45 million recommendation queries monthly for 5 million customers with consistent sub-100ms response times.

↑167%

INCREASE

Conversion rate surge

Conversion rates improved from 1.5% to 4%, representing a 167% increase and millions in additional annual revenue.

↑30%

RETENTION

Customer retention boost

Personalised experiences fostered customer loyalty, with repeat purchases increasing by 30% across their 5 million customer base.

99.99%

uptime

Perfect reliability

Maintained 99.99% uptime even during peak shopping periods, processing millions of queries without performance degradation.

MORE CASE STUDIES

See what other teams have shipped

From knowledge graphs to AI assistants - how enterprise teams are building on the context layer.

Samsung

Unlocking insights with knowledge graphs

Samsung Ads uses SurrealDB to build dynamic, real-time knowledge graphs for smarter campaign execution - collapsing three legacy data stores into one.

Read case study

Verizon

AI assistant empowering 10,000 technicians

Verizon uses SurrealDB to power a generative AI assistant for 10,000 field technicians, delivering instant access to documentation, outage updates, and workflows.

Read case study

Tencent