PERBANDINGAN AKURASI KLASIFIKASI MENGGUNAKAN ALGORITMA QUEST PADA PADA SKENARIO DATA KODIFIKASI DAN NON-KODIFIKASI

Surya Prangga (Universitas Mulawarman)
Rito Goejantoro (Universitas Mulawarman)
Memi Nor Hayati (Universitas Mulawarman)
Siti Mahmuda (Universitas Mulawarman)
Dwi Husnul Mubiin (Universitas Mulawarman)

Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika
Vol. 5 No. 1 (2024): Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistik

Traffic accidents are difficult to predict in terms of when and where will occur. The number of traffic accident cases in Indonesia is relatively high. Regarding on data from the Central Statistics Agency (Badan Pusat Statistik) from 2020 until 2021, the average number of traffic accidents reaches one hundred thousand cases every year. Especially, in the Samarinda City, which is the capital of East Kalimantan Province, it ranked the highest in 2020 compared to several other regencies and cities within East Kalimantan Province. Considering these facts, traffic accident cases need to be addressed to minimize accident-related casualties. One data mining technique used to analyze traffic accident patterns is the decision tree-based classification method. One of the decision tree-based classification methods is QUEST algorithm. The QUEST algorithm (Quick, Unbiased, Efficient, and Statistical Tree) can be used to classify the status of traffic accident victims. Based on data analysis, the best accuracy to classify the status of traffic accident victims was obtained using second scenario data with 80:20 data split, with an accuracy of 66,10% and an F1-Score of 62,96%.