Product-based Neural Networks for User Response Prediction

TL;DR

This paper introduces Product-based Neural Networks (PNN), a deep learning model designed to effectively capture feature interactions in high-dimensional categorical data for user response prediction, outperforming existing models.

Contribution

The paper presents a novel PNN architecture that combines embedding, product, and fully connected layers to improve modeling of feature interactions in sparse categorical data.

Findings

PNN outperforms state-of-the-art models on large-scale ad click datasets.

PNN effectively captures high-order feature interactions.

Experimental results demonstrate superior predictive performance.

Abstract

Predicting user responses, such as clicks and conversions, is of great importance and has found its usage in many Web applications including recommender systems, web search and online advertising. The data in those applications is mostly categorical and contains multiple fields; a typical representation is to transform it into a high-dimensional sparse binary feature representation via one-hot encoding. Facing with the extreme sparsity, traditional models may limit their capacity of mining shallow patterns from the data, i.e. low-order feature combinations. Deep models like deep neural networks, on the other hand, cannot be directly applied for the high-dimensional input because of the huge feature space. In this paper, we propose a Product-based Neural Networks (PNN) with an embedding layer to learn a distributed representation of the categorical data, a product layer to capture interactive patterns between inter-field categories, and further fully connected layers to explore high-order feature interactions. Our experimental results on two large-scale real-world ad click datasets demonstrate that PNNs consistently outperform the state-of-the-art models on various metrics.