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.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2019
- DOI:
- arXiv:
- arXiv:1904.05165
- Bibcode:
- 2019arXiv190405165B
- Keywords:
-
- Computer Science - Information Retrieval
- E-Print:
- Accepted to the International Joint Conferences on Artificial Intelligence (IJCAI) Sister Conference Best Paper Track