The LSTM-EMPG Model for Next Basket Recommendation in E-commerce

Engy Samir El-Shaer; Gerard Thomas McKee; Abeer Hamdy

doi:doi:10.11648/j.ijics.20240901.12

Research Article |

| Peer-Reviewed

The LSTM-EMPG Model for Next Basket Recommendation in E-commerce

Engy Samir El-Shaer^*

, Gerard Thomas McKee

, Abeer Hamdy

Published in International Journal of Information and Communication Sciences (Volume 9, Issue 1)

Received: 6 June 2024 Accepted: 4 July 2024 Published: 15 July 2024

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing sequential patterns in user behavior and accurately utilizing previous purchase information. These challenges can be addressed using Long Short-Term Memory Networks (LSTMs). Nevertheless, LSTMs alone may not fully capture users' repetitive purchase behavior or consider the exact timing of purchases. To account for these limitations, Probabilistic Models such as the Modified Poisson Gamma model (MPG) can be employed. The research reported in this paper proposes and investigates a new approach for the next basket recommendation based on the integration of LSTM with an enhanced Modified Poisson Gamma model to enhance next basket recommendation accuracy in e-commerce. The enhanced model (EMPG) includes a refinement of the MPG model to increase its predictive accuracy, and its recommendations are then integrated with an LSTM network to optimize the LSTM’s predictions. The proposed hybrid LSTM-EMPG model has been evaluated on the Instacart dataset and has produced superior results compared to the Multi-period LSTM, the GRU-based model. DREAM (RNN), and DREAM (LSTM) in terms of predictive accuracy, achieving a higher precision and recall.

Published in	International Journal of Information and Communication Sciences (Volume 9, Issue 1)
DOI	10.11648/j.ijics.20240901.12
Page(s)	9-23
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Deep Learning, Next Basket Recommendation, LSTM, Enhanced Modified Poisson Gamma, Changing Customer Preferences

References

[1]	K. Ong, S.-C. Haw and K.-W. Ng, "Deep Learning Based-Recommendation System: An Overview on Models, Datasets, Evaluation Metrics, and Future Trends," in The 2nd International Conference on Computational Intelligence and Intelligent Systems, 2019. https://doi.org/10.1145/3372422.3372444
[2]	S. Khusro, Z. Ali and I. Ullah, "Recommender Systems: Issues, Challenges, and Research Opportunities," Information Science and Applications, p. 12, 2016 https://doi.org/10.1007/978-981-10-0557-2_112
[3]	F. Y. F. Isinkaye and B. Ojokoh, "Recommendation systems: Principles, methods and evaluation," Egyptian Informatics Journal, p. 14, 2015. https://doi.org/10.1016/j.eij.2015.06.005
[4]	Y. Zhou and T. Ushiama, "LSTM-based Recommendation Approach for Interaction Records," 2019. https://doi.org/10.1007/978-3-030-19063-7_74
[5]	P. K. Singh, P. K. D. Pramanik, A. K. Dey and P. Choudhury, "Recommender Systems: An Overview, Research Trends, and Future Directions," International Journal of Business and Systems Research, vol. 15, p. 40, 2021. https://doi.org/10.1504/IJBSR.2021.10033303
[6]	M. Madhukar, "Challenges & Limitation in Recommender Systems," International Journal of Latest Trends in Engineering and Technology (IJLTET), p. 5, 2014.
[7]	A. Kumar and A. Sharma, "Alleviating Sparsity and Scalability Issues in Collaborative Filtering Based Recommender Systems," in Proceedings of the International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA), Berlin, 2013. https://doi.org/10.1007/978-3-642-35314-7_13
[8]	Q. Zhang and Y. Jin, "Artificial intelligence in recommender systems," Complex & Intelligent Systems, p. 19, 2020. https://doi.org/10.1007/s40747-020-00212-w
[9]	P. Castellsa and D. Jannach, "Recommender Systems: A Primer," in Advanced Topics for Information Retrieval, Madrid, 2023.
[10]	S. Zhang, L. YAO, A. SUN and Y. TAY, "Deep Learning Based Recommender System: A Survey and New Perspectives," in ACM Computing Surveys, 2018. https://doi.org/10.1145/3285029
[11]	R. Devooght and H. Bersini, "Long and Short-Term Recommendations with Recurrent Neural Networks," in the 25th Conference, Slovakia, 2017. https://doi.org/10.1145/3079628.3079670
[12]	P. S. Fader, B. G. S. Hardie and K. L. Lee, "RFM and CLV: Using Iso-value Curves for Customer Base Analysis," Journal of Marketing Research, vol. 42, no. 4, p. 40, 2005. https://doi.org/10.1509/jmkr.2005.42.4.415
[13]	T. Neifer, D. Lawo, G. Stevens, A. Boden and A. Gadatsch, "Recommender Systems in Food Retail: Modeling Repeat Purchase Decisions on Transaction Data of a Stationary Food Retailer," in 18th International Conference on e-Business, 2021. https://doi.org/10.5220/0010553600002997
[14]	R. Bhagat, S. Muralidharan, A. Lobzhanidze and S. Vishwanath, "Buy It Again: Modeling Repeat Purchase Recommendations," Applied Data Science Track Paper, p. 9, 2018. https://doi.org/10.1145/3219819.3219891
[15]	S. Wang, Q. Zhang, L. Hu, X. Zhang, Y. Wang and C. Aggarwal, "Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities," in Association for Computing Machinery, Madrid, 2022. https://doi.org/10.1145/3477495.3532685
[16]	R. Wang, J. L. a. b and Y. Jiang, "Session-based recommendation with time-aware neural attention network," Expert Systems With Applications, p. 10, 2022. https://doi.org/10.1016/j.eswa.2022.118395
[17]	D. AFCHAR, A. B. MELCHIORRE and M. SCHEDL, "Explainability in Music Recommender Systems," in Johannes Kepler University and Linz Institute, Linz, 2022. https://doi.org/10.1002/aaai.12056
[18]	B. Choe, T. Kang and K. Jung, "Recommendation System With Hierarchical Recurrent Neural Network for Long-Term Time Series," in Department of Electrical and Computer Engineering, Seoul, 2021. https://doi.org/10.1109/ACCESS.2021.3079922
[19]	T. Donkers, B. Loepp and J. Ziegler, "Sequential User-based Recurrent Neural Network Recommendations," in RecSys’17, Como, 2017. https://doi.org/10.1145/3109859.3109877
[20]	S. Rendle and C. Freudenthaler, "Factorizing Personalized Markov Chains for Next-Basket Recommendation," in International World Wide Web Conference, North Carolina, 2010. https://doi.org/10.1145/1772690.1772773
[21]	M. Ananyeva, O. Lashinin, V. Ivanova, S. Kolesnikov and D. I. Ignatov, "Towards Interaction-based User Embeddings in Sequential Recommender Models," 2022.
[22]	H. I. Lee, H. S. M. Young Choi and J. K. Kim, "A Multi-Period Product Recommender System," Sustainability, p. 13, 2020. https://doi.org/10.3390/su12030969
[23]	F. Yu, Q. Liu, S. Wu, L. Wang and T. Tan, "A Dynamic Recurrent Model for Next Basket Recommendation," in Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, 2015. https://doi.org/10.1145/2911451.2914683
[24]	L. v. Maasakkers, D. F. b and B. Donkers, "Next-basket prediction in a high-dimensional setting using gated recurrent units," in Expert Systems with Applications, Netherlands, 2023. https://doi.org/10.1016/j.eswa.2022.118795
[25]	J. Wu, Y. Li, L. Shi, L. Yang, X. N. and W. Zhang, "ReRec: A Divide-and-Conquer Approach to Recommendation Based on Repeat Purchase Behaviors of Users in Community E-Commerce," in Mathematical Optimization and Evolutionary Algorithms with Applications, 2022. https://doi.org/10.3390/math10020208
[26]	Y. Zhang, M. Shirakawa and T. Hara, "A Probabilistic Model for Predicting E-commerce Purchases from Emerging Local and Social Interests," in ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, Melbourne, 2020. https://doi.org/10.1109/WIIAT50758.2020.00049
[27]	Z. LIN and H. Chen, "Recommendation over time: a probabilistic model of time-aware recommender systems," in Science China Information Sciences, 2019. https://doi.org/10.1007/s11432-018-9915-8
[28]	M. Li, M. B. Dias, W. El-Deredy and P. J. G. Lisboa, "A Probabilistic Model for Item-Based Recommender Systems," in RecSys’07, 2014. https://doi.org/10.1145/1297231.1297253
[29]	H. Ogura, H. Amano and M. Kondo, "Gamma-Poisson Distribution Model for Text Categorization," ISRN Artificial Intelligence, p. 18, 2013. https://doi.org/10.1155/2013/829630
[30]	E. d. S. d. Silva, H. Langseth and H. Ramampiaro, "Content-Based Social Recommendation with Poisson Matrix Factorization," Norwegian University of Science and Technology, p. 17, 2017. https://doi.org/10.1007/978-3-319-71249-9_32
[31]	W. Zhang and J. Wang, "A Collective Bayesian Poisson Factorization Model for Cold-start Local Event Recommendation," Department of Computer Science and Technology, p. 10, 2015. https://doi.org/10.1145/2783258.2783336
[32]	H. Yu, "Latent Factor Model for Book Recommendation System - Taking Douban as an Example," in International Conference on Education Science and Economic Development (ICESED 2019), 2019. https://doi.org/10.2991/icesed-19.2020.5
[33]	The instacart online grocery shopping dataset, 2018. [Online]. Available: https://www.instacart.com/datasets/grocery-shopping-2017
[34]	E. S. El-Shaer, G. T. McKee and A. Hamdy, "A Hybrid LSTM and Probabilistic Model for Modeling Repeat Purchase Behavior," in 2023 International Conference on Computer and Applications (ICCA), Cairo, 2023. https://doi.org/10.1109/ICCA59364.2023.10401585
[35]	Q. Shambour, "A deep learning based algorithm for multi-criteria recommender," Knowledge-Based Systems, p. 8, 2020. https://doi.org/10.1016/j.knosys.2020.106545

Cite This Article

Plain Text BibTeX RIS

APA Style

El-Shaer, E. S., McKee, G. T., Hamdy, A. (2024). The LSTM-EMPG Model for Next Basket Recommendation in E-commerce. International Journal of Information and Communication Sciences, 9(1), 9-23. https://doi.org/10.11648/j.ijics.20240901.12

Copy | Download

ACS Style

El-Shaer, E. S.; McKee, G. T.; Hamdy, A. The LSTM-EMPG Model for Next Basket Recommendation in E-commerce. Int. J. Inf. Commun. Sci. 2024, 9(1), 9-23. doi: 10.11648/j.ijics.20240901.12

Copy | Download

AMA Style

El-Shaer ES, McKee GT, Hamdy A. The LSTM-EMPG Model for Next Basket Recommendation in E-commerce. Int J Inf Commun Sci. 2024;9(1):9-23. doi: 10.11648/j.ijics.20240901.12

Copy | Download

@article{10.11648/j.ijics.20240901.12,
  author = {Engy Samir El-Shaer and Gerard Thomas McKee and Abeer Hamdy},
  title = {The LSTM-EMPG Model for Next Basket Recommendation in E-commerce
},
  journal = {International Journal of Information and Communication Sciences},
  volume = {9},
  number = {1},
  pages = {9-23},
  doi = {10.11648/j.ijics.20240901.12},
  url = {https://doi.org/10.11648/j.ijics.20240901.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijics.20240901.12},
  abstract = {Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing sequential patterns in user behavior and accurately utilizing previous purchase information. These challenges can be addressed using Long Short-Term Memory Networks (LSTMs). Nevertheless, LSTMs alone may not fully capture users' repetitive purchase behavior or consider the exact timing of purchases. To account for these limitations, Probabilistic Models such as the Modified Poisson Gamma model (MPG) can be employed. The research reported in this paper proposes and investigates a new approach for the next basket recommendation based on the integration of LSTM with an enhanced Modified Poisson Gamma model to enhance next basket recommendation accuracy in e-commerce. The enhanced model (EMPG) includes a refinement of the MPG model to increase its predictive accuracy, and its recommendations are then integrated with an LSTM network to optimize the LSTM’s predictions. The proposed hybrid LSTM-EMPG model has been evaluated on the Instacart dataset and has produced superior results compared to the Multi-period LSTM, the GRU-based model. DREAM (RNN), and DREAM (LSTM) in terms of predictive accuracy, achieving a higher precision and recall.
},
 year = {2024}
}

Copy | Download

TY  - JOUR
T1  - The LSTM-EMPG Model for Next Basket Recommendation in E-commerce

AU  - Engy Samir El-Shaer
AU  - Gerard Thomas McKee
AU  - Abeer Hamdy
Y1  - 2024/07/15
PY  - 2024
N1  - https://doi.org/10.11648/j.ijics.20240901.12
DO  - 10.11648/j.ijics.20240901.12
T2  - International Journal of Information and Communication Sciences
JF  - International Journal of Information and Communication Sciences
JO  - International Journal of Information and Communication Sciences
SP  - 9
EP  - 23
PB  - Science Publishing Group
SN  - 2575-1719
UR  - https://doi.org/10.11648/j.ijics.20240901.12
AB  - Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing sequential patterns in user behavior and accurately utilizing previous purchase information. These challenges can be addressed using Long Short-Term Memory Networks (LSTMs). Nevertheless, LSTMs alone may not fully capture users' repetitive purchase behavior or consider the exact timing of purchases. To account for these limitations, Probabilistic Models such as the Modified Poisson Gamma model (MPG) can be employed. The research reported in this paper proposes and investigates a new approach for the next basket recommendation based on the integration of LSTM with an enhanced Modified Poisson Gamma model to enhance next basket recommendation accuracy in e-commerce. The enhanced model (EMPG) includes a refinement of the MPG model to increase its predictive accuracy, and its recommendations are then integrated with an LSTM network to optimize the LSTM’s predictions. The proposed hybrid LSTM-EMPG model has been evaluated on the Instacart dataset and has produced superior results compared to the Multi-period LSTM, the GRU-based model. DREAM (RNN), and DREAM (LSTM) in terms of predictive accuracy, achieving a higher precision and recall.

VL  - 9
IS  - 1
ER  -

Copy | Download

Author Information

Engy Samir El-Shaer

Informatics and Computer Science, The British University in Egypt, Cairo, Egypt

Contact Email

http://orcid.org/0009-0007-8896-9885
Gerard Thomas McKee

Informatics and Computer Science, The British University in Egypt, Cairo, Egypt

Contact Email

http://orcid.org/0000-0002-7538-7321
Abeer Hamdy

Informatics and Computer Science, The British University in Egypt, Cairo, Egypt

Contact Email

http://orcid.org/0000-0002-0208-3722

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

El-Shaer, E. S., McKee, G. T., Hamdy, A. (2024). The LSTM-EMPG Model for Next Basket Recommendation in E-commerce. International Journal of Information and Communication Sciences, 9(1), 9-23. https://doi.org/10.11648/j.ijics.20240901.12

Copy | Download

ACS Style

El-Shaer, E. S.; McKee, G. T.; Hamdy, A. The LSTM-EMPG Model for Next Basket Recommendation in E-commerce. Int. J. Inf. Commun. Sci. 2024, 9(1), 9-23. doi: 10.11648/j.ijics.20240901.12

Copy | Download

AMA Style

El-Shaer ES, McKee GT, Hamdy A. The LSTM-EMPG Model for Next Basket Recommendation in E-commerce. Int J Inf Commun Sci. 2024;9(1):9-23. doi: 10.11648/j.ijics.20240901.12

Copy | Download

@article{10.11648/j.ijics.20240901.12,
  author = {Engy Samir El-Shaer and Gerard Thomas McKee and Abeer Hamdy},
  title = {The LSTM-EMPG Model for Next Basket Recommendation in E-commerce
},
  journal = {International Journal of Information and Communication Sciences},
  volume = {9},
  number = {1},
  pages = {9-23},
  doi = {10.11648/j.ijics.20240901.12},
  url = {https://doi.org/10.11648/j.ijics.20240901.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijics.20240901.12},
  abstract = {Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing sequential patterns in user behavior and accurately utilizing previous purchase information. These challenges can be addressed using Long Short-Term Memory Networks (LSTMs). Nevertheless, LSTMs alone may not fully capture users' repetitive purchase behavior or consider the exact timing of purchases. To account for these limitations, Probabilistic Models such as the Modified Poisson Gamma model (MPG) can be employed. The research reported in this paper proposes and investigates a new approach for the next basket recommendation based on the integration of LSTM with an enhanced Modified Poisson Gamma model to enhance next basket recommendation accuracy in e-commerce. The enhanced model (EMPG) includes a refinement of the MPG model to increase its predictive accuracy, and its recommendations are then integrated with an LSTM network to optimize the LSTM’s predictions. The proposed hybrid LSTM-EMPG model has been evaluated on the Instacart dataset and has produced superior results compared to the Multi-period LSTM, the GRU-based model. DREAM (RNN), and DREAM (LSTM) in terms of predictive accuracy, achieving a higher precision and recall.
},
 year = {2024}
}

Copy | Download

TY  - JOUR
T1  - The LSTM-EMPG Model for Next Basket Recommendation in E-commerce

AU  - Engy Samir El-Shaer
AU  - Gerard Thomas McKee
AU  - Abeer Hamdy
Y1  - 2024/07/15
PY  - 2024
N1  - https://doi.org/10.11648/j.ijics.20240901.12
DO  - 10.11648/j.ijics.20240901.12
T2  - International Journal of Information and Communication Sciences
JF  - International Journal of Information and Communication Sciences
JO  - International Journal of Information and Communication Sciences
SP  - 9
EP  - 23
PB  - Science Publishing Group
SN  - 2575-1719
UR  - https://doi.org/10.11648/j.ijics.20240901.12
AB  - Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing sequential patterns in user behavior and accurately utilizing previous purchase information. These challenges can be addressed using Long Short-Term Memory Networks (LSTMs). Nevertheless, LSTMs alone may not fully capture users' repetitive purchase behavior or consider the exact timing of purchases. To account for these limitations, Probabilistic Models such as the Modified Poisson Gamma model (MPG) can be employed. The research reported in this paper proposes and investigates a new approach for the next basket recommendation based on the integration of LSTM with an enhanced Modified Poisson Gamma model to enhance next basket recommendation accuracy in e-commerce. The enhanced model (EMPG) includes a refinement of the MPG model to increase its predictive accuracy, and its recommendations are then integrated with an LSTM network to optimize the LSTM’s predictions. The proposed hybrid LSTM-EMPG model has been evaluated on the Instacart dataset and has produced superior results compared to the Multi-period LSTM, the GRU-based model. DREAM (RNN), and DREAM (LSTM) in terms of predictive accuracy, achieving a higher precision and recall.

VL  - 9
IS  - 1
ER  -

Copy | Download