Comparison of Borda and NRF (Normalized Rating Frequency) in Recommender System

Taufiq Abidin (Politeknik Harapan Bersama, Tegal, Indonesia)
Slamet Wiyono (Politeknik Harapan Bersama, Tegal, Indonesia)

JOMLAI: Journal of Machine Learning and Artificial Intelligence
Vol. 1 No. 3 (2022): September

The Collaborative Filtering method is a popular method in making recommender systems. Although CF is a popular method, it has major problems, namely cold start and sparsity . Several studies have been conducted to treat cold starts and sparsity. One way to overcome cold start and sparsity is the Borda calculation method. Research using the Borda method has been carried out a lot but has not utilized the rating optimally. The NRF method is a new method offered to maximize the use of ratings. By using dummy test data, the NRF method is more effective than Borda in calculating recommendation scores.