Programs
- M. Tech. in Automotive Engineering -
- Clinical Fellowship in Laboratory Genetics & Genomics - Fellowship
Publication Type : Conference Proceedings
Publisher : IEEE
Source : International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT)
Url : https://ieeexplore.ieee.org/abstract/document/10053435
Campus : Amritapuri
School : School of Computing
Center : Algorithms and Computing Systems
Year : 2023
Abstract : Recommendation systems are crucial in offering items, particularly in streaming services. Recommendation algorithms are essential for streaming movie services like Netflix in aiding consumers in identifying new movies to watch. Provide a Technologically advanced strategy on autoencoders for constructing a movie filter system that anticipates users’ ratings for movies through vast end-users rating data. Examine the application of deep learning to predict customers’ assessments of new movies using the Movie-Lens dataset, providing movie recommendations. The movie recommendation system proposed here uses particle filtering embedded in a knowledge graph. The model enables the user to provide the best suitable recommendation of movies considering the user’s favorite directors and genre. The experimental findings reveal that compared by error, our recommendation system beats a user-based model on projected ratings and even in the survey where people assess between concepts from both systems.
Cite this Research Publication : Nair, Lekshmi S., and Jo Cheriyan. "Multi-Featured Movie Recommendation Using Knowledge Graph." In 2023 International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), pp. 590-594. IEEE, 2023.