G-STO: Sequential Main Shopping Intention Detection via Graph-Regularized Stochastic Transformer

TL;DR

This paper introduces G-STO, a novel graph-regularized stochastic Transformer model that detects users' main shopping intentions from sequential interactions, improving recommendation accuracy in e-commerce.

Contribution

The paper proposes a new stochastic Gaussian embedding approach with graph regularization for intention detection, enhancing sequential recommendation models.

Findings

G-STO outperforms baselines by 18.08% in Hit@1

Achieves 7.01% improvement in Hit@10

Improves NDCG@10 by 6.11%

Abstract

Sequential recommendation requires understanding the dynamic patterns of users' behaviors, contexts, and preferences from their historical interactions. Most existing works focus on modeling user-item interactions only from the item level, ignoring that they are driven by latent shopping intentions (e.g., ballpoint pens, miniatures, etc). The detection of the underlying shopping intentions of users based on their historical interactions is a crucial aspect for e-commerce platforms, such as Amazon, to enhance the convenience and efficiency of their customers' shopping experiences. Despite its significance, the area of main shopping intention detection remains under-investigated in the academic literature. To fill this gap, we propose a graph-regularized stochastic Transformer method, G-STO. By considering intentions as sets of products and user preferences as compositions of intentions, we model both of them as stochastic Gaussian embeddings in the latent representation space. Instead of training the stochastic representations from scratch, we develop a global intention relational graph as prior knowledge for regularization, allowing relevant shopping intentions to be distributionally close. Finally, we feed the newly regularized stochastic embeddings into Transformer-based models to encode sequential information from the intention transitions. We evaluate our main shopping intention identification model on three different real-world datasets, where G-STO achieves significantly superior performances to the baselines by 18.08% in Hit@1, 7.01% in Hit@10, and 6.11% in NDCG@10 on average.