Akademik Veri Yönetim Sistemi
JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, cilt.36, sa.4, ss.1949-1962, 2021 (SCI-Expanded)
In order to survive in today's global competitive environment, companies must aim for low delivery time, low cost, high quality, and high flexibility in their production. Companies engaged in project-based production should prefer the order-based production method to achieve these goals. For order-based production method, it is very important that the product is ready at the delivery date. To reduce delivery dates, factors affecting production time should be determined. Determining the factors affecting the production time enables companies to plan the improvements that can be made on these factors. On an application, it is shown that data mining can be used to identify the factors affecting production times in metal industry. While investigating these factors, various classification algorithms were used. In the result best evaluation metrics were obtained with random tree algorithm. The features that best express the model used are part name, machine name, month of production, average temperature, operator name, machine size and product quantity. With the information produced, improvement recommendations that can be applied to the production processes are given to the company. The raw data set can be accessed as a supplementary file.