BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals

TL;DR

This paper introduces BLOB, a Bayesian probabilistic model that effectively combines organic browsing data and bandit feedback signals to enhance recommendation accuracy and learning efficiency.

Contribution

The paper presents a novel Bayesian model that integrates organic and bandit signals using variational auto-encoders, improving recommendation quality over existing methods.

Findings

Outperforms state-of-the-art organic recommendation algorithms.

Matches or exceeds bandit-based methods in various environments.

Efficiently leverages organic signals to learn from bandit feedback.

Abstract

A common task for recommender systems is to build a pro le of the interests of a user from items in their browsing history and later to recommend items to the user from the same catalog. The users' behavior consists of two parts: the sequence of items that they viewed without intervention (the organic part) and the sequences of items recommended to them and their outcome (the bandit part). In this paper, we propose Bayesian Latent Organic Bandit model (BLOB), a probabilistic approach to combine the 'or-ganic' and 'bandit' signals in order to improve the estimation of recommendation quality. The bandit signal is valuable as it gives direct feedback of recommendation performance, but the signal quality is very uneven, as it is highly concentrated on the recommendations deemed optimal by the past version of the recom-mender system. In contrast, the organic signal is typically strong and covers most items, but is not always relevant to the recommendation task. In order to leverage the organic signal to e ciently learn the bandit signal in a Bayesian model we identify three fundamental types of distances, namely action-history, action-action and history-history distances. We implement a scalable approximation of the full model using variational auto-encoders and the local re-paramerization trick. We show using extensive simulation studies that our method out-performs or matches the value of both state-of-the-art organic-based recommendation algorithms, and of bandit-based methods (both value and policy-based) both in organic and bandit-rich environments.