DEVELOPMENT OF AN ADVANCED E-COMMERCE PRODUCT RECOMMENDATION SYSTEM USING MACHINE LEARNING

Sameen Shehbaz; Muhammad Ukasha Tahir Siddiqui; Naeem Aslam; Hafiz Muhammad Ijaz; Muhammad Fuzail

Authors

Sameen Shehbaz Department of Computer Science, NFC Institute of Engineering and Technology, Multan, Pakistan.
Muhammad Ukasha Tahir Siddiqui School of Management Management, Scotland Rural College (SRUC), Uk.
Naeem Aslam Department of Computer Science, NFC Institute of Engineering and technology, Multan, Pakistan.
Hafiz Muhammad Ijaz Department of Information Technology, The Islamia University of Bahawalpur, Pakistan.
Muhammad Fuzail Department of Computer Science, NFC Institute of Engineering and technology, Multan, Pakistan.

Keywords:

: E-commerce, Recommendation Systems, Machine Learning, Deep Learning, Collaborative Filtering, Content-Based Filtering, Hybrid Models, Neural Collaborative Filtering

Abstract

This research presents the development of an advanced recommendation system leveraging machine learning techniques to enhance personalized user experiences. The system integrates collaborative filtering, content-based filtering, and hybrid approaches to provide accurate and efficient recommendations across diverse domains. A benchmark dataset was utilized for training and evaluation, and multiple machine learning algorithms were tested to identify the most suitable model. Experimental results demonstrate significant improvements in recommendation accuracy compared to conventional methods. The study highlights the importance of feature engineering, similarity measures, and hybrid strategies in overcoming limitations of traditional approaches. The proposed system provides a scalable, adaptive, and reliable framework that can be applied in real-world applications such as e-commerce, digital marketing, and online platforms.