Perbandingan Algoritma SVM dan Decision Tree Dalam Klasifikasi Kepuasan Pengguna Aplikasi Migo E-Bike di Playstore

Abstract

Currently, transportation has become an essential need in daily life, and the rapid development of digital technology has had a significant impact on the use of services and interaction with mobile applications, including in the transportation sector. The Migo E-Bike app is the first electric bike rental service application in Indonesia, offering environmentally friendly services to reduce air pollution. This research aims to assess the effectiveness of two data mining algorithms, SVM and Decision Tree, in classifying user satisfaction of the Migo E-Bike app based on reviews and ratings on the Playstore. The research findings indicate that the Decision Tree algorithm performs better than SVM. The Decision Tree achieved an accuracy of 76.39%, with balanced precision and recall for both satisfaction categories. In contrast, SVM exhibited significant imbalance with an overall accuracy of only 51.25%. Therefore, the Decision Tree algorithm is more effective in handling the user rating dataset for the Migo E-Bike app.