NORMA eResearch @NCI Library

A Deep Learning Recommender System for Anime

Mutteppagol, Vidyashree Mahaling (2021) A Deep Learning Recommender System for Anime. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (987kB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (507kB) | Preview


The extensive market available and the rising popularity of the anime industry necessitate a dedicated research study to help build a recommender system that can generate personalized and accurate anime recommendations for users. The prominent machine learning models such as the k-nearest neighbours, content-based, collaborative filtering, autoencoders and hybrid models, that are often used in recommender systems have a huge potential for development. These models experience data sparsity and cold-start issues and there is an opportunity for improvement in their predictive accuracies as well. As a result, a recommender system with a Deep Learning collaborative filtering-based model is proposed in this research which provides anime recommendations that are highly relevant to the users’ likes and interests. This model will pre-process the data and transform it employing the techniques of embedding and batch normalization. The anime dataset used in the research is obtained from the open-source platform -Kaggle. The top anime recommendations are generated for the user in three cases -User-based CF model, Item-based CF model and our proposed Model-based CF using Deep Learning and the results are qualitatively measured and found to be very close to the interests of the users. In addition to generating the anime recommendations, the proposed model is evaluated using the metrics of Mean Squared Error (MSE) and Mean Absolute Error (MAE). The closer to zero values obtained for these metrics of MSE and MAE indicates that the model performs efficiently.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Deep Learning; Collaborative Filtering; Anime; Data Sparsity; Recommender Systems; Cold-start
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 11 Dec 2021 10:32
Last Modified: 11 Dec 2021 10:32

Actions (login required)

View Item View Item