Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems

TL;DR

This paper addresses delayed outcome prediction in recommender systems by leveraging proxies through neural network architectures, improving regret minimization and robustness in real-world human behavior prediction tasks.

Contribution

It introduces two neural network models, FF and RFF, that utilize proxies to enhance delayed outcome prediction, with RFF being robust to non-informative proxies.

Findings

RFF outperforms FF and direct forecasters on real datasets.

Proxies via factorization effectively mitigate long delay impacts.

The approach improves regret bounds in adversarial delayed online learning.

Abstract

Predicting delayed outcomes is an important problem in recommender systems (e.g., if customers will finish reading an ebook). We formalize the problem as an adversarial, delayed online learning problem and consider how a proxy for the delayed outcome (e.g., if customers read a third of the book in 24 hours) can help minimize regret, even though the proxy is not available when making a prediction. Motivated by our regret analysis, we propose two neural network architectures: Factored Forecaster (FF) which is ideal if the proxy is informative of the outcome in hindsight, and Residual Factored Forecaster (RFF) that is robust to a non-informative proxy. Experiments on two real-world datasets for predicting human behavior show that RFF outperforms both FF and a direct forecaster that does not make use of the proxy. Our results suggest that exploiting proxies by factorization is a promising way to mitigate the impact of long delays in human-behavior prediction tasks.