Book Recommendation Using Collaborative Filtering Algorithm

The explosive growth in the amount of available digital information in higher education has created a potential challenge of information overload, which hampers timely access to items of interest. The recommender systems are applied in different domains such as recommendations film, tourist advising, webpages, news, songs, and products. But the recommender systems pay less attention to university library services. The most users of university library are students. These users have a lack of ability to search and select the appropriate materials from the large repository that meet for their needs. A lot of work has been done on recommender system, but there are technical gaps observed in existing works such as the problem of constant item list in using web usage mining, decision tree induction, and association rule mining. Besides, it is observed that there is cold start problem in case-based reasoning approach. Therefore, this research work presents matrix factorization collaborative filtering with some performance enhancement to overcome cold start problem. In addition, it presents a comparative study among memory-based and model-based approaches. In this study, researchers used design science research method. The study dataset, 5189 records and 76,888 ratings, was collected from the University of Gondar student information system and online catalogue system. To develop the proposed model, memory-based and model-based approaches have been tested. In memory-based approach, matrix factorization collaborative filtering with some performance enhancements has been implemented. In model-based approach, K-nearest neighbour (KNN) and singular value decomposition (SVD) algorithms are also assessed experimentally. The SVD model is trained on our dataset optimized with a scored RMSE 0.1623 compared to RMSE 0.1991 before the optimization. The RMSE for a KNN model trained using the same dataset was 1.0535. This indicates that the matrix factorization performs better than KNN models in building collaborative filtering recommenders. The proposed SVD-based model accuracy score is 85%. The accuracy score of KNN model is 53%. So, the comparative study indicates that matrix factorization technique, specifically SVD algorithm, outperforms over neighbourhood-based recommenders. Moreover, using hyperparameter tuning with SVD also has an improvement on model performance compared with the existing SVD algorithm.