ML-Based Product Recommendation System Using Browsing History, Purchase Data, and Seasonal Trends. |
Author(s): |
| Harshitha H B , ATME College of Engineering; Hajeera Firdose, ATME College of Engineering; T. Varsha Nanjappa, ATME College of Engineering; Tasbiya Taskin, ATME College of Engineering; Yashas a P, ATME College of Engineering |
Keywords: |
| Recommendation System, Machine Learning, User Behavior Analysis, Product Recommendation, Similarity-Based Filtering, Seasonal Demand Analysis |
Abstract |
|
This paper presents the development of a machine-learning–based recommendation system that predicts and suggests products to users based on browsing history, purchase patterns, and seasonal buying trends. The system analyses user–item interactions, extracts meaningful behavioural features, and recommends products through similarity-based ML techniques. Seasonal demand is included to enhance prediction accuracy. The proposed model demonstrates that even a lightweight, interpretable ML approach can generate relevant and personalized product recommendations suitable for small e-commerce datasets. |
Other Details |
|
Paper ID: IJSRDV13I100036 Published in: Volume : 13, Issue : 10 Publication Date: 01/01/2026 Page(s): 25-26 |
Article Preview |
|
|
|
|
