What Users Want? WARHOL: A Generative Model for Recommendation

TL;DR

WARHOL is a generative model that predicts user preferences and creates new, relevant products by learning distributions over product features, enhancing recommendation systems with product generation capabilities.

Contribution

Introduces WARHOL, a generative architecture that models product features to generate new relevant products based on user preferences, bridging recommendation and product creation.

Findings

WARHOL approaches state-of-the-art recommendation performance

It can generate new products relevant to user profiles

Demonstrates the potential of generative models in recommendation systems

Abstract

Current recommendation approaches help online merchants predict, for each visiting user, which subset of their existing products is the most relevant. However, besides being interested in matching users with existing products, merchants are also interested in understanding their users' underlying preferences. This could indeed help them produce or acquire better matching products in the future. We argue that existing recommendation models cannot directly be used to predict the optimal combination of features that will make new products serve better the needs of the target audience. To tackle this, we turn to generative models, which allow us to learn explicitly distributions over product feature combinations both in text and visual space. We develop WARHOL, a product generation and recommendation architecture that takes as input past user shopping activity and generates relevant textual and visual descriptions of novel products. We show that WARHOL can approach the performance of state-of-the-art recommendation models, while being able to generate entirely new products that are relevant to the given user profiles.