Practical Policy Optimization with Personalized Experimentation
This addresses the need for more effective experimentation in organizations dealing with diverse user responses, though it appears incremental by building on existing HTE modeling and policy optimization methods.
The paper tackles the problem of standard experimentation platforms not optimizing for heterogeneous treatment effects (HTEs) in user populations by introducing a personalized experimentation framework (PEX) that optimizes treatment assignments at the user level to improve multiple outcomes, with practical implementation demonstrated using open-source software.
Many organizations measure treatment effects via an experimentation platform to evaluate the casual effect of product variations prior to full-scale deployment. However, standard experimentation platforms do not perform optimally for end user populations that exhibit heterogeneous treatment effects (HTEs). Here we present a personalized experimentation framework, Personalized Experiments (PEX), which optimizes treatment group assignment at the user level via HTE modeling and sequential decision policy optimization to optimize multiple short-term and long-term outcomes simultaneously. We describe an end-to-end workflow that has proven to be successful in practice and can be readily implemented using open-source software.