Implementation of Item-Based Collaborative Filtering Algorithm for Blangkon Product Recommendation on Web-Based E-commerce System

In the development of technology at this time, especially in the trade sector, there is no escape from the development of information technology which has had a significant impact. The most obvious form in the development of information technology in the trade sector is e-commerce, which allows transactions between sellers and buyers to be easier. Not only that, the problem now is that users must be spoiled with features that help to recommend user desires. This requires a recommendation system to help select user desires based on products with high ratings. Therefore, it must continue to develop a system that has features to support the sales system. To achieve the system needs to require a method that supports such as using the collaborative filtering method. This method focuses the analysis on similarities between items, because it is more stable and not always sensitive to changing data with a large number of users. The collaborative filtering method is used in the recommendation system to predict inter-user preferences for blangkon products based on the similarity of other user patterns, so that product recommendations appear that they have never seen or bought before. This technique uses an item-based model in it. The results of the performance test to determine the level of prediction accuracy of the method in this study using the mean absolute error. With MAE for three times trying to get a value of 0.5, 0.3 and 0.2.