Cover Image

Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System

Recommender systems are essential engines to deliver product recommendations for e-commerce businesses. Successful adoption of recommender systems could significantly influence the growth of marketing targets. Collaborative filtering is a type of recommender system model that uses customers' ac...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanafi, Mohd Aboobaider, Burhanuddin
Format: Article
Language:English
Published: Hindawi Limited 2021
Online Access:http://eprints.utem.edu.my/id/eprint/25705/2/HANAFIBURHANWORD%20SEQUENTIAL%20USING%20DEEP%20LSTM.PDF
http://eprints.utem.edu.my/id/eprint/25705/
https://downloads.hindawi.com/journals/cin/2021/8751173.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utem.eprints.25705
record_format eprints
spelling my.utem.eprints.257052022-03-15T16:14:23Z http://eprints.utem.edu.my/id/eprint/25705/ Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System Hanafi Mohd Aboobaider, Burhanuddin Recommender systems are essential engines to deliver product recommendations for e-commerce businesses. Successful adoption of recommender systems could significantly influence the growth of marketing targets. Collaborative filtering is a type of recommender system model that uses customers' activities in the past, such as ratings. Unfortunately, the number of ratings collected from customers is sparse, amounting to less than 4%. The latent factor model is a kind of collaborative filtering that involves matrix factorization to generate rating predictions. However, using only matrix factorization would result in an inaccurate recommendation. Several models include product review documents to increase the effectiveness of their rating prediction. Most of them use methods such as TF-IDF and LDA to interpret product review documents. However, traditional models such as LDA and TF-IDF face some shortcomings, in that they show a less contextual understanding of the document. This research integrated matrix factorization and novel models to interpret and understand product review documents using LSTM and word embedding. According to the experiment report, this model significantly outperformed the traditional latent factor model by more than 16% on an average and achieved 1% on an average based on RMSE evaluation metrics, compared to the previous best performance. Contextual insight of the product review document is an important aspect to improve performance in a sparse rating matrix. In the future work, generating contextual insight using bidirectional word sequential is required to increase the performance of e-commerce recommender systems with sparse data issues. Hindawi Limited 2021-12 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/25705/2/HANAFIBURHANWORD%20SEQUENTIAL%20USING%20DEEP%20LSTM.PDF Hanafi and Mohd Aboobaider, Burhanuddin (2021) Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System. Computational Intelligence and Neuroscience, 2021. pp. 1-20. ISSN 1687-5265 https://downloads.hindawi.com/journals/cin/2021/8751173.pdf 10.1155/2021/8751173
institution Universiti Teknikal Malaysia Melaka
building UTEM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknikal Malaysia Melaka
content_source UTEM Institutional Repository
url_provider http://eprints.utem.edu.my/
language English
description Recommender systems are essential engines to deliver product recommendations for e-commerce businesses. Successful adoption of recommender systems could significantly influence the growth of marketing targets. Collaborative filtering is a type of recommender system model that uses customers' activities in the past, such as ratings. Unfortunately, the number of ratings collected from customers is sparse, amounting to less than 4%. The latent factor model is a kind of collaborative filtering that involves matrix factorization to generate rating predictions. However, using only matrix factorization would result in an inaccurate recommendation. Several models include product review documents to increase the effectiveness of their rating prediction. Most of them use methods such as TF-IDF and LDA to interpret product review documents. However, traditional models such as LDA and TF-IDF face some shortcomings, in that they show a less contextual understanding of the document. This research integrated matrix factorization and novel models to interpret and understand product review documents using LSTM and word embedding. According to the experiment report, this model significantly outperformed the traditional latent factor model by more than 16% on an average and achieved 1% on an average based on RMSE evaluation metrics, compared to the previous best performance. Contextual insight of the product review document is an important aspect to improve performance in a sparse rating matrix. In the future work, generating contextual insight using bidirectional word sequential is required to increase the performance of e-commerce recommender systems with sparse data issues.
format Article
author Hanafi
Mohd Aboobaider, Burhanuddin
spellingShingle Hanafi
Mohd Aboobaider, Burhanuddin
Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System
author_facet Hanafi
Mohd Aboobaider, Burhanuddin
author_sort Hanafi
title Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System
title_short Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System
title_full Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System
title_fullStr Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System
title_full_unstemmed Word Sequential Using Deep LSTM And Matrix Factorization To Handle Rating Sparse Data For E-Commerce Recommender System
title_sort word sequential using deep lstm and matrix factorization to handle rating sparse data for e-commerce recommender system
publisher Hindawi Limited
publishDate 2021
url http://eprints.utem.edu.my/id/eprint/25705/2/HANAFIBURHANWORD%20SEQUENTIAL%20USING%20DEEP%20LSTM.PDF
http://eprints.utem.edu.my/id/eprint/25705/
https://downloads.hindawi.com/journals/cin/2021/8751173.pdf
_version_ 1728055210364895232
score 13.23648

Similar Items