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{145520,
        author = {M.Reddi Prasanna and J S.Ananda Kumar},
        title = {Movie Recommender System},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {4},
        number = {10},
        pages = {743-746},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=145520},
        abstract = {Research on recommendation systems has gained a considerable quantity of attention over the past decade because the variety of on-line users and on-line contents still grow at an exponential rate. With the evolution of the social internet, individuals generate and consume data in real time using on-line services like Twitter, Facebook, and internet news portals. With the rapidly growing on-line community, web-based retail systems and social media sites have to process many variant user requests per day. Generating quality recommendations using this large quantity of knowledge is itself a really difficult task. Nonetheless, critical thewweb-based retailers like Amazon and Netflix, the preceding social networking sites got to face further challenge once generating recommendations as their contents are very rapidly ever-changing. Therefore, providing recent info within the least amount of time may be a major objective of such recommender systems.  Though cooperative filtering may be a widely used technique in recommendation systems, generating the advice model using this approach may be an expensive task, and often done offline. Hence, it's tough to use cooperative filtering within the presence of dynamically ever-changing contents; per systems need frequent updates to the advice model to keep up the accuracy and therefore the freshness of the recommendations. power of graphic processing units (gpus) will be wont to method massive volumes of knowledge with dynamically ever-changing contents in real time, and accelerate the advice method for social media knowledge streams. During this paper, we address the problem of rapidly changing contents, and propose a parallel on-the-fly cooperative Filtering algorithmic rule victimization gpus to facilitate frequent updates to the recommendations model. We use a hybrid similarity calculation methodology by combining the item–item cooperative filtering with item class info and temporal info. The experimental results on real-world datasets show that the planned algorithm outperformed many existing on-line CF algorithms in terms of accuracy, memory consumption, and runtime. It had been additionally discovered that the planned algorithm scaled well with the information rate an},
        keywords = {Recommender system, collaborative filtering, power of graphic processing units.},
        month = {},
        }