search for


A study on predictive model for forecasting anti-aircraft missile spare parts demand based on machine learning
Journal of the Korean Data & Information Science Society 2019;30:587-96
Published online May 31, 2019;
© 2019 Korean Data and Information Science Society.

Jaedong Kim1 · Hanjun Lee2

1Korea Institute for Defense Analyses, 2Linton School of Global Business, Hannam University
Correspondence to: Assistant professor, Linton School of Global Business, Hannam University, 70 Hannam-ro, Daedeok-gu, Daejeon 34430, Korea. E-mail:
Received March 5, 2019; Revised April 17, 2019; Accepted April 24, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Spare parts demand forecasting is one of the most critical tasks in logistics, because it considerably affects the efficiency of defense budget execution. Although time series methods have been the most common approach in prior studies, there is still room for improvement in terms of the prediction accuracy. In this study, we gathered 17,451,247 component consumption data including structured and unstructured data from the Defense Logistics Integrated Information System. Using the data, we propose demand forecasting models based on data mining and text mining methods. The results show that our approach can improve the prediction performance compared to that of existing approaches.
Keywords : Data mining, demand forecasting, spare part, text mining, time series.