Please use this identifier to cite or link to this item:

Double Deep Features for Apparel Recommendation System

File Size Format  
0437.pdf 357.33 kB Adobe PDF View/Open

Item Summary

Title:Double Deep Features for Apparel Recommendation System
Authors:Lu, Yichi
Duan, Yufeng
Saga, Ryosuke
Keywords:Social Shopping: The Good, the Bad, and the Ugly
convolutional neural network
deep learning
image shape feature
probabilistic matrix factorization
show 1 morerecommender system
show less
Date Issued:07 Jan 2020
Abstract:This study describes a recommendation system embedded in the double features extracted by convolutional neural networks (CNNs). Several probabilistic models, such as probabilistic matrix factorization (PMF)-based approaches, have been utilized for recommendation systems based on a CNN model. Each recommendation algorithm utilizes a single CNN model to extract precise features about documents and pictures, and the systems with CNN have contributed in improving the performance in rating prediction. Meanwhile, the systems for some items should consider at least two precise features simultaneously, and the extension to embed multiple CNN models is necessary. However, methods that integrate multiple CNN-based features into existing recommendation systems, such as PMF, are not available. Thus, this study proposes a novel probabilistic model that integrates double CNNs into PMF. For apparel goods, two trained CNNs from document and image shape features are combined, and the latent variables of users and items are optimized based on the vectorized features of CNNs and rating. Extensive experiments demonstrate that our model outperforms other recommendation models.
Pages/Duration:8 pages
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections: Social Shopping: The Good, the Bad, and the Ugly

Please email if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons