Saved in:
Bibliographic Details
Main Author: Gauri Parvati, Pavithran M A, Sooraj Sajeev, Prof. Asha J George, Prof. Manju Mathews
Format: Recurso digital
Language:
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.15129756
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901644470386688
author Gauri Parvati, Pavithran M A, Sooraj Sajeev, Prof. Asha J George, Prof. Manju Mathews
author_facet Gauri Parvati, Pavithran M A, Sooraj Sajeev, Prof. Asha J George, Prof. Manju Mathews
contents <p>—The growing need for accurate recommendations<br> has motivated the devel opment of hybrid recommendation<br> systems. In this project, we propose a sys tem that integrates<br> collaborative filtering, content-based filtering, and knowledge<br> graph approaches to enhance recommendation accuracy and<br> address limitations such as cold-start and data sparsity. The<br> system uses a multi-step method: col laborative filtering predicts<br> user preferences based on similar users, content-based filtering<br> analyses item attributes, and a knowledge graph refines recom<br>mendations by leveraging relational data. The hybrid approach<br> offers advantages like more personalized recommendations and<br> better handling of sparse data. However, it has the drawback of<br> increased computational complexity due to integrating multiple<br> algorithms. In conclusion, the system aims to effectively combines<br> the strengths of different recommendation techniques, to provide<br> more precise and relevant suggestions to users.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15129756
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle RecMe: A Personal Hybrid Recommendation System
Gauri Parvati, Pavithran M A, Sooraj Sajeev, Prof. Asha J George, Prof. Manju Mathews
<p>—The growing need for accurate recommendations<br> has motivated the devel opment of hybrid recommendation<br> systems. In this project, we propose a sys tem that integrates<br> collaborative filtering, content-based filtering, and knowledge<br> graph approaches to enhance recommendation accuracy and<br> address limitations such as cold-start and data sparsity. The<br> system uses a multi-step method: col laborative filtering predicts<br> user preferences based on similar users, content-based filtering<br> analyses item attributes, and a knowledge graph refines recom<br>mendations by leveraging relational data. The hybrid approach<br> offers advantages like more personalized recommendations and<br> better handling of sparse data. However, it has the drawback of<br> increased computational complexity due to integrating multiple<br> algorithms. In conclusion, the system aims to effectively combines<br> the strengths of different recommendation techniques, to provide<br> more precise and relevant suggestions to users.</p>
title RecMe: A Personal Hybrid Recommendation System
url https://doi.org/10.5281/zenodo.15129756