This Author published in this journals
All Journal Infotech Journal
Ni Kadek Juliani
Universitas Primakara

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

PENERAPAN DATA MINING UNTUK MENENTUKAN KELAYAKAN KENDARAAN SEPEDA MOTOR BEKAS MENGGUNAKAN ALGORITMA C4.5 Ni Kadek Juliani; Ni Made Satvika Iswari; Nengah Widya Utami
INFOTECH journal Vol. 11 No. 2 (2025)
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/infotech.v11i2.15338

Abstract

Determining the feasibility of used motorcycles is one of the challenges for companies in selecting attributes that cover various factors, such as physical condition, maintenance history, and reasonable price. In this study, the researcher aims to analyze the existing problems and provide decision results by applying the C4.5 algorithm to determine the feasibility of used motorcycles based on relevant data. The C4.5 algorithm has the capability to build decision trees to automate and improve the accuracy of the feasibility determination process. In this research, attributes such as motorcycle model, year, engine, kilometers, fuel type, modifications, engine overhaul, oil type, transmission, engine type, and displacement are used as determining variables.Furthermore, to avoid overfitting that may occur due to overly complex decision trees, the researcher also applies pruning techniques to the C4.5 algorithm. Pruning functions to trim insignificant branches of the tree so that the model becomes simpler. With pruning, it is expected that the resulting decision tree will be not only accurate but also efficient, enabling the feasibility determination process of used motorcycles to be conducted optimally. Therefore, after applying pruning techniques, the model achieved an accuracy of 72.41%, precision of 68.42%, recall of 86.67%, and F1-score of 76.47%.