• Mr. Anant Kumar Dixit
• Mr. Kamalendra Verma

Streaming platforms (video/audio) depend heavily on recommender systems to personalize content, increase engagement, and reduce churn. This paper surveys the machine-learning algorithms commonly used in streaming-service recommender systems, compares classical and modern approaches (collaborative filtering, matrix factorization, neural models, session-based RNNs, Transformer-based sequential models, and graph neural networks), describes evaluation metrics and engineering considerations unique to streaming, and outlines an experimental evaluation plan and recommendation for production deployment. Key strengths, weaknesses, and practical trade-offs for each class of algorithm are discussed.

recommender systems, streaming services, collaborative filtering, matrix factorization, RNN, Transformer, graph neural networks, personalization,deep neural network.

"Machine Learning Algorithms Used for Recommender Systems in Streaming Services", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.e487-e495, November-2025, Available :http://www.jetir.org/papers/JETIR2511462.pdf

"Machine Learning Algorithms Used for Recommender Systems in Streaming Services", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppe487-e495, November-2025, Available at : http://www.jetir.org/papers/JETIR2511462.pdf