A Session-Based Customer Preference Learning Method by Using the Gated Recurrent Units With Attention Function

Abstract

In this paper, we investigate an attention function combined with the gated recurrent units (GRUs), named GRUA, to raise the accuracy of the customer preference prediction. The attention function extracts the important product features by using the time-bias parameter and the term frequency-inverse document frequency parameter for recommending products to a customer in the ongoing session. We show that the attention function with the GRUs can learn the customer's intention in the ongoing session more precisely than the existing session-based recommendation (SBR) methods. The experimental results show that the GRUA outperforms two SBR methods: the stacked denoising autoencoders with collaborative filtering (SDAE/CF) and the GRUs with collaborative filtering (GRU/CF) based on the precision and recall evaluation metrics. The data from three publicly available datasets, the Amazon Product Review dataset, the Xing dataset, and the Yoo-Choose Click dataset, are used to evaluate the performance of the GRUA with the SDAE/CF and the GRU/CF. This paper shows that adopting the attention function into the GRUs can dramatically increase the accuracy of the product recommendation in the SBR.

Preference-aware Task Assignment in Spatial Crowdsourcing: from Individuals to Groups

“…Although a few researches explore workers' preferences for tasks in crowdsourcing [1], [2], [45], they just infer workers' preferences from past task-performing patterns or explicit feedbacks without considering workers' temporal preferences for different tasks. In other research areas, e.g., personalized product recommendation, some work uses new techniques of machine learning to learn users' preferences [3]. For example, Quadrana et al [30] introduce the usage of Gated Recurrent Units (GRUs) with the collaborative filtering method for learning users' preferences, where GRU is a new generation of Recurrent Neural Network (RNN) and regarded as a variant of Long Short-Term Memory (LSTM) network [9].…”

“…GRUs can reduce the computational burden and perform as good as LSTM [10]. [3] learns a user's preferences from his/her ongoing session (such as the user's behaviors, meta data of the products, etc.) by using the Gated Recurrent Units (GRUs) with attention function.…”

A novel Based-Approach Composed of Clustering Algorithm & Cosine Similarity for Products Recommendation

“…proposed two various algorithms to improve the recommendation performance [21]. Beside that Chen et al examined an attention function merged with the gated recurrent to increase the accuracy of the customer preference [22]. According to the research work achieved by [23], it obtained that the content recommender system limitation was in the early stage, which mainly related to insufficient data.…”

Neural Session-Aware Recommendation

“…RNNs remain popular modeling tools for session data in newer works with a number of modifications and improvements made to the original RNN architecture, e.g. using more suitable objective functions [17], applying data augmentation techniques [34], incorporating content features [15], [26], or adding attention mechanisms to capture the user's purpose [7], [21]. Other deep learning architectures have also been explored to model session sequences.…”