RESTAURANT RECOMMENDER SYSTEM USING ITEM BASED COLLABORATIVE FILTERING AND ADJUSTED COSINE ALGORITHM SIMILARITY

Abstract

In 2018, the Ministry of Industry (Kemenperin) stated that the food and beverage sector contributed 6.34% of the national gross domestic product (GDP). Currently, culinary information can be easily found, both in print and online. The amount of information available sometimes makes people over-informed, making it difficult to choose a restaurant based on their preferences. To assist consumers in selecting a restaurant, we need a system that can provide several recommendations. This study aims to implement the item-based Collaborative Filtering method using the Adjusted Cosine Similarity algorithm on a restaurant recommendation system. The test was carried out with 40 samples from UIN Syarif Hidayatullah Jakarta using purposive sampling because the sample was selected based on specific criteria, and 40 respondents can be said to be correct because of the minimum number of respondents is 30. The accuracy test uses precision, and the determination of the error value uses MAE. The analysis of the research results used three scenarios, which are 5, 20, and 40 users. The third scenario produces the best precision and MAE values. Precision is better if the precision value is close to 1, and MAE is getting better if the MAE value is getting closer to 0. So it can be concluded that the Item-Based method with the Adjusted Cosine algorithm has the best accuracy and error values when the number of users grows.