Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce
Boosting the sales of e-commerce services is guaranteed once users find more items matching their interests in a short amount of time. Consequently, recommendation systems have become a crucial part of any successful e-commerce service. Although various recommendation techniques could be used in e-c...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/24/11/1575 |
_version_ | 1797468354123923456 |
---|---|
author | Mohamed Maher Perseverance Munga Ngoy Aleksandrs Rebriks Cagri Ozcinar Josue Cuevas Rajasekhar Sanagavarapu Gholamreza Anbarjafari |
author_facet | Mohamed Maher Perseverance Munga Ngoy Aleksandrs Rebriks Cagri Ozcinar Josue Cuevas Rajasekhar Sanagavarapu Gholamreza Anbarjafari |
author_sort | Mohamed Maher |
collection | DOAJ |
description | Boosting the sales of e-commerce services is guaranteed once users find more items matching their interests in a short amount of time. Consequently, recommendation systems have become a crucial part of any successful e-commerce service. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems in recent years. This growing interest is due to security concerns over collecting personalized user behavior data, especially due to recent general data protection regulations. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with their preferences. Our extensive experiments investigate baseline techniques (e.g., nearest neighbors and pattern mining algorithms) and deep learning approaches (e.g., recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most scenarios. However, we found that these models suffer more in the case of long sessions when there exists drift in user interests, and when there are not enough data to correctly model different items during training. Our study suggests that using the hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field. |
first_indexed | 2024-03-09T19:05:16Z |
format | Article |
id | doaj.art-3c802a32eb294694aea7046fac6f8dcb |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-09T19:05:16Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-3c802a32eb294694aea7046fac6f8dcb2023-11-24T04:36:28ZengMDPI AGEntropy1099-43002022-10-012411157510.3390/e24111575Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-CommerceMohamed Maher0Perseverance Munga Ngoy1Aleksandrs Rebriks2Cagri Ozcinar3Josue Cuevas4Rajasekhar Sanagavarapu5Gholamreza Anbarjafari6iCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaiCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaMachine Learning Group, Big Data Department, Rakuten Inc., Tokyo 158-0094, JapanMachine Learning Group, Big Data Department, Rakuten Inc., Tokyo 158-0094, JapaniCV Lab, Institute of Technology, University of Tartu, 51009 Tartu, EstoniaBoosting the sales of e-commerce services is guaranteed once users find more items matching their interests in a short amount of time. Consequently, recommendation systems have become a crucial part of any successful e-commerce service. Although various recommendation techniques could be used in e-commerce, a considerable amount of attention has been drawn to session-based recommendation systems in recent years. This growing interest is due to security concerns over collecting personalized user behavior data, especially due to recent general data protection regulations. In this work, we present a comprehensive evaluation of the state-of-the-art deep learning approaches used in the session-based recommendation. In session-based recommendation, a recommendation system counts on the sequence of events made by a user within the same session to predict and endorse other items that are more likely to correlate with their preferences. Our extensive experiments investigate baseline techniques (e.g., nearest neighbors and pattern mining algorithms) and deep learning approaches (e.g., recurrent neural networks, graph neural networks, and attention-based networks). Our evaluations show that advanced neural-based models and session-based nearest neighbor algorithms outperform the baseline techniques in most scenarios. However, we found that these models suffer more in the case of long sessions when there exists drift in user interests, and when there are not enough data to correctly model different items during training. Our study suggests that using the hybrid models of different approaches combined with baseline algorithms could lead to substantial results in session-based recommendations based on dataset characteristics. We also discuss the drawbacks of current session-based recommendation algorithms and further open research directions in this field.https://www.mdpi.com/1099-4300/24/11/1575session-based recommendationinformation systemsdeep learningevaluationE-commerce |
spellingShingle | Mohamed Maher Perseverance Munga Ngoy Aleksandrs Rebriks Cagri Ozcinar Josue Cuevas Rajasekhar Sanagavarapu Gholamreza Anbarjafari Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce Entropy session-based recommendation information systems deep learning evaluation E-commerce |
title | Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce |
title_full | Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce |
title_fullStr | Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce |
title_full_unstemmed | Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce |
title_short | Comprehensive Empirical Evaluation of Deep Learning Approaches for Session-Based Recommendation in E-Commerce |
title_sort | comprehensive empirical evaluation of deep learning approaches for session based recommendation in e commerce |
topic | session-based recommendation information systems deep learning evaluation E-commerce |
url | https://www.mdpi.com/1099-4300/24/11/1575 |
work_keys_str_mv | AT mohamedmaher comprehensiveempiricalevaluationofdeeplearningapproachesforsessionbasedrecommendationinecommerce AT perseverancemungangoy comprehensiveempiricalevaluationofdeeplearningapproachesforsessionbasedrecommendationinecommerce AT aleksandrsrebriks comprehensiveempiricalevaluationofdeeplearningapproachesforsessionbasedrecommendationinecommerce AT cagriozcinar comprehensiveempiricalevaluationofdeeplearningapproachesforsessionbasedrecommendationinecommerce AT josuecuevas comprehensiveempiricalevaluationofdeeplearningapproachesforsessionbasedrecommendationinecommerce AT rajasekharsanagavarapu comprehensiveempiricalevaluationofdeeplearningapproachesforsessionbasedrecommendationinecommerce AT gholamrezaanbarjafari comprehensiveempiricalevaluationofdeeplearningapproachesforsessionbasedrecommendationinecommerce |