Neural Autoregressive Collaborative Filtering for Implicit Feedback

TL;DR

This paper introduces implicit CF-NADE, a neural autoregressive model for collaborative filtering with implicit feedback, demonstrating superior performance over traditional matrix factorization methods on streaming service data.

Contribution

The paper presents a novel neural autoregressive model for implicit feedback, converting user interactions into like and confidence vectors for improved recommendation accuracy.

Findings

Implicit CF-NADE outperforms baseline matrix factorization methods.

The model effectively handles implicit feedback data.

Experimental results validate the model's superior performance.

Abstract

This paper proposes implicit CF-NADE, a neural autoregressive model for collaborative filtering tasks using implicit feedback ( e.g. click, watch, browse behaviors). We first convert a users implicit feedback into a like vector and a confidence vector, and then model the probability of the like vector, weighted by the confidence vector. The training objective of implicit CF-NADE is to maximize a weighted negative log-likelihood. We test the performance of implicit CF-NADE on a dataset collected from a popular digital TV streaming service. More specifically, in the experiments, we describe how to convert watch counts into implicit relative rating, and feed into implicit CF-NADE. Then we compare the performance of implicit CF-NADE model with the popular implicit matrix factorization approach. Experimental results show that implicit CF-NADE significantly outperforms the baseline.