Implementasi Data Mining untuk Klasifikasi Status Pembayaran Pelanggan Menggunakan Algoritma Decision Tree

Aedo, Yesha Daniela
Rahman, Abdul

MDP Student Conference
Vol 5 No 2 (2026): The 5th MDP Student Conference 2026

This study aims to classify customer payment status using the C4.5 Decision Tree algorithm. The classification is divided into two classes, namely paid and overdue, using a dataset of 9,220 transaction records from the 2021–2023 period. The main problem faced by the company is frequent delays in customer payments, which affect accounts receivable management. Therefore, a system is needed to identify payment status based on the sales representatives handling the customers. The data used include order date, order type, sales name, total price, payment method, and payment status. The C4.5 algorithm constructs a decision tree based on entropy and the highest information gain values. The evaluation results show an accuracy of 91.73%, precision of 91.75%, recall of 91.95%, and an F1-score of 92.35%, indicating that the proposed model has good performance and is suitable as a decision support tool for the company.