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

Authors : Emmanuel Ndidi Osegi, Kingsley Ezebunwo Igbudu, Hachikaru Ngozi Okwu

Pages : 144-152

Doi:10.53070/bbd.1673090

View : 51 | Download : 126

Publication Date : 2025-12-01

Article Type : Research Paper

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

ORIGINAL ARTICLE URL