TSMOO: Solving Multi-Objective Experimentation with Constrained Thompson Sampling
TL;DR
This work introduces TSMOO (Thompson Sampling with Multi-Objective Optimization), a method that bridges the gap by combining multi-metric optimization with continuous learning in batch traffic allocation and outperforming both single-metric and elimination-based baselines.
Abstract
Traditional online A/B experimentation limits the number of treatments that can be evaluated concurrently. Bandit-based adaptive experimentation algorithms address this by dynamically reallocating traffic across an order of magnitude more treatments. Yet existing methods involve a fundamental trade-off: single-metric Thompson Sampling-based methods are robust to novelty effects but cannot accommodate multiple launch criteria, while elimination-based multi-objective methods support multiple constraints but risk prematurely removing promising treatments. We introduce TSMOO (Thompson Sampling with Multi-Objective Optimization), a method that bridges this gap by combining multi-metric optimization with continuous learning. Grounded in stochastically constrained best-arm identification, TSMOO extends single-metric Thompson Sampling to multi-objective batch traffic allocation by estimating multi-constraint feasibility at each allocation step, while preserving all treatments throughout exploration. It further incorporates uplift modeling that mitigates temporal effects shared across treatments and control and ensures that the Gaussian distribution assumption holds. In simulations replaying historical real-world experimentation patterns, TSMOO achieves 93-94% success rates in multi-winner settings and 63-66% under novelty effects, outperforming both single-metric and elimination-based baselines.