Causal Recommender Systems for Sequential Decision-Making
Recommender systems (RS) are intended to be a personalized decision support tool, where decisions can take the form of products to buy (e.g., Amazon), movies to watch (e.g., Netflix), online news to read (e.g., Google News), or even individuals to screen for a medical condition (e.g., personalized medicine). For digital users, RS play an essential role, since the available content (and hence possible actions) grows exponentially. While such systems can prove useful, they carry inherent biases which can be detrimental since RS tend to reinforce and validate the preferences of users (a phenomenon known as echo chambers), without consideration for the notion of diversity of users with niche preferences. To counter these difficulties, we propose to use tools from causal inference in order to model the feedback loops inherent in recommender systems. We also propose to bridge the existing theory of causal inference (specific to biostatistics and epidemiology) with the classic problems associated with recommender systems (specific to machine learning).