Hybrid Machine Learning Based Recommendation System for OTT Platform

Harsh Porwal; Mrs. Kiran Patel

Hybrid Machine Learning Based Recommendation System for OTT Platform

Author(s)	Harsh Porwal, Mrs. Kiran Patel
Country	India
Abstract	This paper is dedicated to the creation of a recommendation system on Over-the-Top (OTT) platform based on the analysis of user behavior and multiple filtering strategies. The system incorporates collaborative filtering, content-based filtering and demographic methods to come up with personalized movie recommendations. The handling of missing values and the preprocessing of raw user data and the use of statistical techniques, which include the use of cosine similarity and TF-IDF vectorization, are used to identify the meaningful patterns in the viewing preferences. There are metadata attributes connected with the recommendations, including casting, directors, keywords, genres, etc. that enhance the recommendations and increase the prediction quality. The study points to the fact that hybrid recommendation systems can address the weaknesses of classic ones, including sparsity, cold-start issues, and extreme computation fees. The outcomes of experimental evidence prove the hypothesis that metadata and behavioral analysis are better than individual methods of producing more relevant and varied recommendations. In addition to technical input, this publication focuses on the commercial worth of recommender systems and demonstrates the way in which they can help to boost customer satisfaction, to improve user engagement, and assist data-based marketing efforts in a highly competitive OTT landscape.
Keywords	Recommendation system, OTT platforms, collaborative filtering, content-based filtering, hybrid model, data mining.
Field	Engineering
Published In	Volume 17, Issue 1, January-March 2026
Published On	2026-03-25

View / Download PDF File

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Hybrid Machine Learning Based Recommendation System for OTT Platform

Share this