Daily Product Purchase Predictions with E-commerce Recommendations Using a Continual Learning Neural Network System

Abstract

In this research paper, we propose an intelligent recommender system suitable for E-commerce transactions. The system employs an emerging ANN method called the Hierarchical Temporal Memory (HTM) for continuous predictive recommendation. The results considering open source data obtained from an online store were reported considering the adjustments of HTM columns parameter. The findings of the result indicate that higher columns will lead to enhanced performance with > 95% classification accuracy obtained at a set column size of 1000units. The proposed HTM-ANN is expected to be a promising alternative to existing feed-forward ANNs for real-time E-commerce applications.

Keywords

• ANN
• E-commerce
• Continual Learning
• Prediction
• Recommender System

Daily Product Sales-Orders E-commerce Recommendations and Prediction Using a Continual Learning Neural Machine Learning System

Abstract

In this research paper, we propose an intelligent recommender system suitable for E-commerce transactions. The system employs an emerging ANN method called the Hierarchical Temporal Memory (HTM) for continuous predictive recommendation. The results considering open source data obtained from an online store were reported considering the adjustments of HTM columns parameter. The findings of the result indicate that higher columns will lead to enhanced performance with > 95% classification accuracy obtained at a set column size of 1000units. The proposed HTM-ANN is expected to be a promising alternative to existing feed-forward ANNs for real-time E-commerce applications.

Keywords

• ANN
• E-commerce
• Continual Learning
• Prediction
• Recommender System

References

1. Abonamah, A. A., Tariq, M. U., & Shilbayeh, S. (2021). On the commoditization of artificial intelligence. Frontiers in psychology, 12, 696346.
2. Du, R. Y., Hu, Y., & Damangir, S. (2015). Leveraging trends in online searches for product features in market response modeling. Journal of Marketing, 79(1), 29-43.
3. Gangurde, R. (2017). Optimized predictive model using artificial neural network for market basket analysis.
4. Guo, Y., Yin, C., Li, M., Ren, X., & Liu, P. (2018). Mobile e-commerce recommendation system based on multi-source information fusion for sustainable e-business. Sustainability, 10(1), 147.
5. Hawkins, J., Ahmad, S., Dubinsky, D. (2011). Hierarchical temporal memory including HTM cortical learning algorithms, Technical Report, v0.2.1. https://www.numenta.org/resources/HTM_CorticalLearningAlgorithms.pdf.
6. Hsu, S. C. (2016). Fuzzy time series customers prediction: Case study of an e-commerce cash flow service provider. International Journal of Computational Intelligence and Applications, 15(04), 1650024.
7. Han, J., & Kamber, M. (2006). Data Mining: Concepts and techniques. Morgan Kaufmann Publishers.
8. Hosoz, M., Ertunc, H. M., & Bulgurcu, H. (2011). An adaptive neuro-fuzzy inference system model for predicting the performance of a refrigeration system with a cooling tower. Expert Systems with Applications, 38(11), 14148-14155.

9. Kedia, S., Madan, M., & Borar, S. (2019). Early bird catches the worm: Predicting returns even before purchase in fashion E-commerce. arXiv preprint arXiv:1906.12128.
10. Li, M., Song, J., Wang, G., & Chen, P. (2019). A complex contract negotiation model based on hybrid intelligent algorithm. Cluster Computing, 22(Suppl 6), 14317-14325.
11. Lo, K. (2003). Economic consequences of regulated changes in disclosure: The case of executive compensation. Journal of Accounting and Economics, 35(3), 285-314.
12. Massaro, A., Vitti, V., & Galiano, A. (2018). Model of multiple artificial neural networks oriented on sales prediction and product shelf design. International Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI), 7(3), 1-19.
13. Mountcastle, V. B. (1997). The columnar organization of the neocortex. Brain: a journal of neurology, 120(4), 701-722.
14. Osegi, N. E. (2016). An improved intelligent agent for mining real-time databases using modified cortical learning algorithms. arXiv preprint arXiv:1601.00191.
15. Osegi, E. N. (2021). Using the hierarchical temporal memory spatial pooler for short-term forecasting of electrical load time series. Applied Computing and Informatics, 17(2), 264-278.
16. Osegi, E. N., & Jumbo, E. F. (2021). Comparative analysis of credit card fraud detection in Simulated Annealing trained Artificial Neural Network and Hierarchical Temporal Memory. Machine Learning with Applications, 6, 100080.
17. Sakar, C. O., Polat, S. O., Katircioglu, M., & Kastro, Y. (2019, Dataset). Real-time prediction of online shoppers’ purchasing intention using multilayer perceptron and LSTM recurrent neural networks. Neural Computing and Applications, 31(10), 6893-6908.
18. Shekasta, M., Katz, G., Greenstein-Messica, A., Rokach, L., & Shapira, B. (2019). New item consumption prediction using deep learning. arXiv preprint arXiv:1905.01686.
19. Suchacka, G., Skolimowska-Kulig, M., & Potempa, A. (2015a). A k-nearest neighbors method for classifying user sessions in e-commerce scenario. journal of Telecommunications and Information Technology.
20. Suchacka, G., Skolimowska-Kulig, M., & Potempa, A. (2015b). Classification Of E-Customer Sessions Based On Support Vector Machine. ECMS, 15, 594-600.
21. Suchacka, G., & Stemplewski, S. (2017). Application of neural network to predict purchases in online store. In Information Systems Architecture and Technology: Proceedings of 37th International Conference on Information Systems Architecture and Technology–ISAT 2016–Part IV (pp. 221-231). Springer International Publishing.
22. Usmani, Z. A., Manchekar, S., Malim, T., & Mir, A. (2017, February). A predictive approach for improving the sales of products in e-commerce. In 2017 Third International Conference on Advances in Electrical, Electronics, Information, Communication and Bio-Informatics (AEEICB) (pp. 188-192). IEEE.
23. Zhang, B., Tan, R., & Lin, C. J. (2021). Forecasting of e-commerce transaction volume using a hybrid of extreme learning machine and improved moth-flame optimization algorithm. Applied Intelligence, 51, 952-965.