Implementation of Data Mining for Raw Material Stock Prediction in Clothing Production Using the C4.5 Algorithm Method

Nur Ismiza (Universitas Malikussaleh)
Lidya Rosnita
Nurdin

Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)

Al-Fatih Convection is a business engaged in the textile industry, located in Baktiya, North Aceh Regency. This company produces various uniforms for schools and workwear. Raw material stock management is a crucial aspect that affects the smoothness of the production process. Currently, the purchase of raw material stock still relies on estimation methods, often leading to excessive or insufficient stock. Therefore, a raw material stock prediction system is needed to optimize stock management.This research aims to implement the C4.5 algorithm to predict raw material stock for clothing production. The method is chosen for its ability to build a predictive model based on attributes such as material type, price, availability, and demand. Using data mining, this study generates a decision tree that helps Al-Fatih Convection prioritize which raw materials should be purchased. The results from the implementation of the C4.5 algorithm show an accuracy rate of 93%, which is expected to help reduce excessive or insufficient stock and improve operational efficiency at Al-Fatih Convection.