Adversarial learning for product recommendation

TL;DR

This paper introduces RecommenderGAN, a novel adversarial network model that learns to generate user behavior data for product recommendation, effectively handling sparse implicit feedback and large product catalogs.

Contribution

The work presents a new conditional, coupled GAN architecture for modeling joint user behavior distributions in recommendation systems, capable of handling large-scale, sparse data.

Findings

Conversion rates ranged from 1.323% to 1.763%.

Results are comparable to industry averages.

Preliminary results suggest utility for consumers and retailers.

Abstract

Product recommendation can be considered as a problem in data fusion-- estimation of the joint distribution between individuals, their behaviors, and goods or services of interest. This work proposes a conditional, coupled generative adversarial network (RecommenderGAN) that learns to produce samples from a joint distribution between (view, buy) behaviors found in extremely sparse implicit feedback training data. User interaction is represented by two matrices having binary-valued elements. In each matrix, nonzero values indicate whether a user viewed or bought a specific item in a given product category, respectively. By encoding actions in this manner, the model is able to represent entire, large scale product catalogs. Conversion rate statistics computed on trained GAN output samples ranged from 1.323 to 1.763 percent. These statistics are found to be significant in comparison to null hypothesis testing results. The results are shown comparable to published conversion rates aggregated across many industries and product types. Our results are preliminary, however they suggest that the recommendations produced by the model may provide utility for consumers and digital retailers.