Sina Sheikholeslami


2021

pdf bib
Siamese Neural Networks for Detecting Complementary Products
Marina Angelovska | Sina Sheikholeslami | Bas Dunn | Amir H. Payberah
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop

Recommender systems play an important role in e-commerce websites as they improve the customer journey by helping the users find what they want at the right moment. In this paper, we focus on identifying a complementary relationship between the products of an e-commerce company. We propose a content-based recommender system for detecting complementary products, using Siamese Neural Networks (SNN). To this end, we implement and compare two different models: Siamese Convolutional Neural Network (CNN) and Siamese Long Short-Term Memory (LSTM). Moreover, we propose an extension of the SNN approach to handling millions of products in a matter of seconds, and we reduce the training time complexity by half. In the experiments, we show that Siamese LSTM can predict complementary products with an accuracy of ~85% using only the product titles.