1School of Economics and Trade, Henan University of Industry Technology, Nanyang City, China, 473000
2School of Architectural Engineering, Henan University of Industry Technology, Nanyang City, China, 473000
Received: June 13, 2026
Accepted: August 08, 2026
Publication Date: September 18, 2026
Block diagram of the suggested AI-based E-commerce Recommendation Framework
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.
Download Citation: BibTeX | http://dx.doi.org/10.6180/jase.202612_35.053
The rapid expansion of e-commerce platforms has increased the need for intelligent recommendation systems capable of accurately modeling complex user behaviors and interaction patterns. This research proposes an AI-based recommendation framework using the Retail Rocket dataset for personalized product recommendation. The dataset is preprocessed through duplicate removal, missing value handling, and Min-Max normalization to ensure reliable feature representation. Adaptive Weighted Holoentropy is introduced for feature extraction by capturing uncertainty, feature dependencies, and behavioral relationships among user interactions. The extracted features are processed using an Enhanced CNN-BiLSTM model to learn local patterns and long-term temporal dependencies. A Scaled Swish activation function is integrated to improve gradient stability and nonlinear learning performance. Based on predicted interaction classes, including View, Add-to-Cart, and Transaction, the recommendation module generates product relevance scores and performs Top-N ranking. Experimental results demonstrate superior classification performance with 0.9794 accuracy, 0.9801 precision, 0.9794 recall, and 0.9794 F1-score. The recommendation evaluation achieves Precision@K of 0.503, Recall@K of 0.350, Hit Rate of 0.829, NDCG of 0.565, and MAP of 0.501, confirming improved recommendation accuracy and personalization.
Keywords: Artificial Intelligence-based Recommendation, Adaptive Holoentropy, Bidirectional Long Short-Term Memory, Convolutional Neural Network, Multi-Class Classification[cite: 17]
- [1] A. R. Onteddu, R. R. Bandhela, and R. R. Kundavaram, (2024) “Enhancing e-commerce product recommendations through data engineering and machine learning” Economic Sciences 20(1): 171-183. DOI: 10.69889/vqgzw857.[cite: 17]
- [2] A. Ahad, R. Mohaimin, M. N. S. Rabbi, et al., (2025) “AI-based product clustering for e-commerce platforms: enhancing navigation and user personalization” International Journal of Environmental Sciences 11: 156-171. URL: https://theaspd.com/index.php.[cite: 17]
- [3] A. Alqhatani and S. B. Khan, (2024) “IoT-driven hybrid deep collaborative transformer with federated learning for personalized e-commerce recommendations: an optimized approach” Scalable Computing: Practice and Experience 25(5): 3408-3426. DOI: 10.12694/scpe.v25i5.3007.[cite: 17]
- [4] A. Bahi, I. Gasmi, S. Bentrad, and R. Khantouchi, (2025) “Enhancing recommendation diversity in e-commerce using Siamese network and cluster-based technique” Bulletin of Electrical Engineering and Informatics 14(2): 1223-1230. DOI: 10.11591/eei.v14i2.8572.[cite: 17]
- [5] M. Chowdhary and P. Chahal, (2025) “Online review-based product recommendation using Mellivora Heron optimization-based BiLSTM model in e-commerce systems” Web Intelligence 23(2): DOI: 10.1177/24056456241297357.[cite: 17]
- [6] W. Cui and H.-K. Lam, (2026) “Fuzzy-enhanced variable weight graph convolutional networks for recommender systems” Computers and Electrical Engineering 131: 110970. DOI: 10.1016/j.compeleceng.2026.110970.[cite: 17]
- [7] S. Dhawan, K. Singh, and M. Yadav, (2025) “Hybrid deep learning recommendation system for accurate movie and product review predictions” Scalable Computing: Practice and Experience 26(4): 1902-1918. DOI: 10.12694/scpe.v26i4.4449.[cite: 17]
- [8] N. Hassan, M. Abdelraouf, and D. El-Shihy, (2025) “The moderating role of personalized recommendations in the trust-satisfaction-loyalty relationship: an empirical study of AI-driven e-commerce” Future Business Journal 11(1): 66. DOI: 10.1186/s43093-025-00476-z.[cite: 17]
- [9] J. Huang, (2025) “Optimization and innovation of AI-based e-commerce platform recommendation system” Journal of Computer, Signal, and System Research 2(6): 66-73. DOI: 10.71222/7bb7rx18.[cite: 17]
- [10] C. Jiang, (2025) “Research on sales forecasting and consumption recommendation system of e-commerce agricultural products based on LSTM model” GeoJournal 90(3): 93. DOI: 10.1007/s10708-025-11342-4.[cite: 17]
- [11] N. Karne, (2021) “Customizing enterprise interactions: an AI-driven approach to customer recommendation systems” International Journal of Scientific Research in Science and Technology 8(1): 325-336. DOI: 10.32628/IJSRST52310110.[cite: 17]
- [12] P. Keikhosrokiani and M. F. Goh, (2024) “A hybrid recommender system for health supplement e-commerce based on customer data implicit ratings” Multimedia Tools and Applications 83(15): 45315-45344. DOI: 10.1007/s11042-023-17321-6.[cite: 17]
- [13] H. U. Khan, A. Naz, F. K. Alarfaj, and N. Almusallam, (2025) “A transformer-based architecture for collaborative filtering modeling in personalized recommender systems” Scientific Reports 15(1): 24503. DOI: 10.1038/s41598-025-08931-1.[cite: 17]
- [14] E. S. P. Krishna, T. B. Ramu, R. K. Chaitanya, et al., (2025) “Enhancing e-commerce recommendations with sentiment analysis using MLA-EDTCNet and collaborative filtering” Scientific Reports 15(1): 6739. DOI: 10.1038/s41598-025-91275-7.[cite: 17]
- [15] M. Sunita and S. V. Mallapur, (2024) “Optimal detection of border gateway protocol anomalies with extensive feature set” Multimedia Tools and Applications 83(17): 50893-50919. DOI: 10.1007/s11042-023-17135-6.[cite: 17]