Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems
This work addresses the challenge of delayed feedback in recommender systems, which is incremental as it builds on existing online learning methods by incorporating proxies to improve prediction accuracy.
The paper tackles the problem of predicting delayed outcomes in recommender systems, such as whether customers will finish reading an ebook, by using proxies like partial engagement to minimize regret in adversarial online learning. It proposes two neural network architectures, with the Residual Factored Forecaster outperforming others on real-world datasets, showing that exploiting proxies through factorization can mitigate long delays in human-behavior prediction.
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.