Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{192709,
        author = {Bolli poojitha and Telugu veera jyoti and Madugundu Varalakshmi and Aradabanda sirisha and J.Mohan kumar and Dr. P. Veeresh},
        title = {Product Recommendation System Using Machine Learning Techniques.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {1955-1960},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192709},
        abstract = {The fast expansion of e-commerce platforms has created an excessive amount of products which prevents users from finding items that suit their preferences. The project introduces Recommend which serves as a smart e-commerce recommendation system that uses machine learning methods together with a Flask web application to provide users with custom product recommendations. The system uses multiple recommendation methods which include content-based filtering and collaborative filtering and hybrid methods and multi-model approaches to enhance both recommendation accuracy and recommendation variety. The system collects product and user interaction information from actual e-commerce datasets which then undergoes preprocessing that includes data cleaning and feature extraction and transformation. Content-based recommendations use product attributes and textual descriptions to analyze products while collaborative filtering models use user behavior patterns which include ratings and interactions to forecast user preferences. Hybrid and multi-model strategies use individual approach strengths to solve two common issues that recommendation systems face which are data sparsity and cold-start problems. A Flask web framework provides seamless integration for model deployment which enables users to authenticate their accounts browse products search items and view real-time recommendations. Customers can use the user-friendly interface to browse products while they receive tailored recommendations that update in real time. The experimental results show that using multiple recommendation methods together improves both relevance and user engagement and complete shopping experience.},
        keywords = {The main elements of this project include E-Commerce Recommendation System and Machine Learning and Collaborative Filtering and Content-Based Filtering and Hybrid Recommendation and Flask Web Application and Personalized Product Recommendation},
        month = {February},
        }