AdaptEx: A Self-Service Contextual Bandit Platform

TL;DR

AdaptEx addresses the need for scalable, fast personalization in Expedia Group by offering a self-service contextual bandit platform that requires no upfront model training. Its architecture decouples decision making, data collection, and model updates with a real-time feedback loop using a Bandit Store and streaming pipelines, while exposing a simple API for teams. The contribution lies in a rich algorithmic toolkit (including TS, EG, IGW, Cascading Bandits, BLR, RLS) and practical mechanisms for latency, cold-start, and multi-objective optimization. This enables rapid, data-driven experiments across diverse products and brands, reducing time to statistically significant improvements compared to conventional A/B tests.

Abstract

This paper presents AdaptEx, a self-service contextual bandit platform widely used at Expedia Group, that leverages multi-armed bandit algorithms to personalize user experiences at scale. AdaptEx considers the unique context of each visitor to select the optimal variants and learns quickly from every interaction they make. It offers a powerful solution to improve user experiences while minimizing the costs and time associated with traditional testing methods. The platform unlocks the ability to iterate towards optimal product solutions quickly, even in ever-changing content and continuous "cold start" situations gracefully.

Figures (1)

• Figure 1: AdaptEx Platform Architecture Overview