PENGGUNAAN METODE COLLABORATIVE FILTERING BASED UNTUK REKOMENDASI KENDARAAN BERMOTOR

Abstract

Motorized vehicles are one of the main needs of every human being and also the most common form of transportation used by people. To choose a motorized vehicle, people should not choosing it in a hurry because it takes good consideration to choose the right brand, type, and the need for the vehicle. In making their choice, usually people will read the reviews from vehicle review sites such as Carmudi.co.id, OTO.com, KobaYogas.com, and so on. The purpose of this thesis is to help provide web-based vehicle recommendations using the values of rating and criteria selected by the user. User rating values are calculated with collaborative filtering. In addition to the rating value, users can also get vehicle recommendations by providing specifications of the vehicle needs. Rating values from the program users will be processed by using adjusted cosine similarity to determine their similarity score to the rating values from vehicle review sites and other users so the vehicle recommendations can be obtained according to the similarity of the other user ratings. Based on the results of User Acceptance Testing (UAT) from 21 respondents, the testing got an average score of 83.95% so the program can be categorized as “Very Good”.