Skripsi
PENERAPAN SUPPORT VECTOR MACHINE PADA METODE COLLABORATIVE FILTERING UNTUK REKOMENDASI ANIME
The increasing number of anime productions with various genres makes it difficult for users to find anime to watch. According to the problems, a recommendation system is needed to provide anime according to the genre preferred by users. The challenges are in the form of data with large dimensions and uneven distribution generating low accuracy and the system running slowly. In order to solve the problem, this research combines collaborative filtering and support vector machines (SVM). The SVM method is used to classify user “likes” and “dislikes”, then the data labeled “dislike” will be deleted to ease the work of the system. Experiment on MyAnimelist data shows higher recommendation results. The test results for the SVM model obtained an accuracy of 93.29%, a precision of 94.07%, and a recall of 98.98%. The test results of the recommendation system by applying the SVM method provide an accuracy rate of 70.25%, a precision of 86.65%, and a recall of 67.32%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307004441 | T87098 | T870982022 | Central Library (REFERENS) | Available but not for loan - Not for Loan |
No other version available