Causal Embeddings for Recommendation: An Extended Abstract

Abstract

Recommendations are commonly used to modify user's natural behavior, for example, increasing product sales or the time spent on a website. This results in a gap between the ultimate business objective and the classical setup where recommendations are optimized to be coherent with past user behavior. To bridge this gap, we propose a new learning setup for recommendation that optimizes for the Incremental Treatment Effect (ITE) of the policy. We show this is equivalent to learning to predict recommendation outcomes under a fully random recommendation policy and propose a new domain adaptation algorithm that learns from logged data containing outcomes from a biased recommendation policy and predicts recommendation outcomes according to random exposure. We compare our method against state-of-the-art factorization methods, in addition to new approaches of causal recommendation and show significant improvements.

Accepted to the International Joint Conferences on Artificial Intelligence (IJCAI) Sister Conference Best Paper Track

References in corpus (5)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Session-based Recommendations with Recurrent Neural Networks
• Learning Representations for Counterfactual Inference
• Recommendations as Treatments: Debiasing Learning and Evaluation
• Predicting Counterfactuals from Large Historical Data and Small Randomized Trials