Your browser does not support the PubReader view.
Go to this page to see a list of supporting browsers.
Korean Academic Society of Business Administration
[ Article ]
korean management review - Vol. 53, No. 4, pp.997-1025
ISSN: 1226-1874 (Print)
Print publication date 31 Aug 2024
Received 27 Dec 2023 Revised 25 Mar 2024 Accepted 24 Apr 2024
DOI: https://doi.org/10.17287/kmr.2024.53.4.997

기계학습 방법을 활용한 가격 예측 모형 개발: 공군 항공유 구매 사례를 기반으로

임세환 ; 민순홍 ; 최경환
(주저자) 연세대학교 이메일
(교신저자) 연세대학교 sminscm@yonsei.ac.kr
(공저자) 방위사업청 borita@hanmail.net
Developing a Machine Learning-Based Model for Price Forecasting: A Case Study on ROKAF Jet Fuel Procurement
Sehwan Lim ; Soonhong Min ; Kyunghwan Choi
(First Author) Yonsei University School of Business limseh@yonsei.ac.kr
(Corresponding Author) Yonsei University School of Business sminscm@yonsei.ac.kr
(Co-Author) Defense Acquisition Program Administration borita@hanmail.net


Copyright 2024 THE KOREAN ACADEMIC SOCIETY OF BUSINESS ADMINISTRATION
This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted, distribution, and reproduction in any medium, provided the original work is properly cited.

초록

공군은 매년 수천억 원 규모의 항공유를 구매 중이며, 급격한 항공유 가격 변동은 작전 준비태세에 리스크 요인으로 작용하고 있다. 정확한 가격 예측은 유류 재고관리를 최적화하는 데 중요하지만, 기존 연구는 구매기관에서 바로 적용이 제한되는 거시적 수준의 경제지표에 초점을 맞추는 경우가 많았다. 본 연구에서는 구매기관 관점에서 항공유 가격 예측 정확도를 향상하기 위한 기계학습 방법의 효과를 평가한다. 이때, 예측 정확도 향상을 위해 공급망, Google 검색 트렌드(Google Trends), 지정학적 요인과 전통적인 경제 요인을 통합한 기계학습 예측모형을 제안한다. 본 연구의 결과는 XGBoost 모형이 RMSE(Root Mean Squared Error)를 67%까지 줄여 가장 정확한 성과를 나타내었다. 따라서 공군을 비롯한 구매기관이 기계학습 가격 예측 모형을 채택하면 공급 가격관리 능력이 크게 향상될 수 있다. 또한, 본 연구 결과는 구매가 반복되고 가격 변동성이 큰 다른 제품 관리에도 효과적으로 적용할 수 있다.

Abstract

The Republic of Korea Air Force (ROKAF) spends hundreds of billions of Korean won annually on jet fuel, with price fluctuations posing a significant logistical and operational readiness challenge. Accurate price forecasting is crucial for optimizing fuel inventory management, yet existing research often focuses on macro-level economic indicators with limited practical application. This study investigates the potential of machine learning (ML) for enhancing jet fuel price forecasting accuracy. We propose ML models incorporating supply chain data, Google Trends data, and geopolitical factors alongside traditional economic variables for more realistic predictions. Our results demonstrate that a XGBoost model achieves the best performance, reducing Root Mean Squared Error (RMSE) by 67%. Adoption of this model by the ROKAF could significantly improve supply price management capabilities. Furthermore, the study's findings have broader applicability, potentially benefiting the inventory management of other commodities with significant price volatility and recurring purchases.

Keywords:

commodities, jet fuel, machine learning, price forecasting, purchasing

키워드:

석유제품, 항공유, 기계학습 방법, 가격 예측, 구매관리

References

  • 김선미, 조두연(2022), “Machine Learning과 Google Trends Data를 이용한 유가 예측 및 분석,” The Korean Journal of Economics, 제29권 2호, pp. 175-193.
    Kim, S., and Cho, D.(2022), “Forecasting Crude Oil Prices with Google Trends Data Based on Machine Learning Methods,” The Korean Journal of Economics, 29(2). pp.175-193. [ https://doi.org/10.46228/KJE.29.2.3 ]
  • 김정욱(2006), “기름값 너무 올라 공군 훈련 차질,” 중앙일보, 2006.03.28.
    Kim, J.(2006). “Oil prices rise too high, disrupting air force training,” The Joongang, 2006.03.28., https://www.joongang.co.kr/article/1658535#home, (’24.1.30.)
  • 노산하, 김남현(2019), “유가 불확실성이 국내 경제변수에 미치는 영향,” 국제경제연구, 제25권 1호, pp.1- 38.
    Noh, S., and Kim, N.(2019), “The Effects of Oil Price Uncertainty on Korean Economic Variables,” International Business Journal, 25(1), pp.1-38. [ https://doi.org/10.17298/kky.2019.25.1.001 ]
  • 선미선, 이성문, 이혁수, 송병규, 오병훈, 권남연, 이미지, 정재원(2016), “무기체계 획득 시 운영유지비 분석체계 발전방안,” 한국국방연구원 연구보고서, 운2016-3882.
    Sun, M., Lee, S., Lee, H., Song, B., Oh, B., Kwon, N., Lee, M., and Jung, J.(2016), “A Study on the Development of Operation Maintenance Cost Analysis System in the Acquisition of Weapon Systems,” KIDA Research Report, 3882.
  • 송경재(2021), “미 항공유 부족에 항공사들 몸살,” 파이낸셜뉴스, 2021.07.28.
    Song, K.(2021), “Airlines are struggling due to US aviation fuel shortage,” Financial News, 2021.07.28., https://www.fnnews.com/news/202107280452179467, (’24.1.30.)
  • 이서진, 유종민(2022), “예측오차의 확률분포에 기반한 국제유가 불확실성 분석,” 에너지경제연구, 제21권 1호, pp. 87-113.
    Lee, S., and Yu, J.(2022), “Causes and Consequences of Oil Price Uncertainty,” Korean Energy Economic Review, 21(1), pp.87-113.
  • 이인애(2022), “VLSFO 가격 750-770 달러 사상 최고: 러-우크라이나 정치외교상황 영향, 정치가 석유 펀더멘털 앞서 원유가 8 년만의 최고수준, HSFO 가격도 7 년전 수준으로 올라,” 해양한국, 제2022권 3호, pp.33-33.
    Lee, I.(2022), “VLSFO price $750-770, all-time high: Russia-Ukraine political and diplomatic situation influenced, politics ahead of oil fundamentals Crude oil is at the highest level in 8 years, HSFO price also rose to the level of 7 years ago,” Maritime Korea, 2022 (3), pp.33-33.
  • 조지성, 이언경, 권보배, 김아롬, 김엄지(2022), “글로벌 공급망 리스크별 영향분석 및 대응방안 연구 - 에너지․곡물을 중심으로,” [KMI] 연구보고서.
    Jo, J., Lee, E., Kwon, B., Kim, A., and Kim, U. (2022), “A Study on Impact Analysis and Response Measures of Global Supply Chain Risks - Focusing on Energy and Crops,” [KMI] Research Report.
  • 한국석유공사(2023), “2023년 국제유가 전망, 2023년 1월 주간 유가전망,” Petronet.
    Korea National Oil Corporation(2023), “international oil price forecast for 2023, weekly oil price forecast for January 2023,” Petronet.
  • Amer, M., Daim, T. U., and Jetter, A.(2013), “A review of scenario planning,” Futures, 46, pp.23-40. [https://doi.org/10.1016/j.futures.2012.10.003]
  • Asche, F., Gjølberg, O., and Völker, T.(2003), “Price relationships in the petroleum market: an analysis of crude oil and refined product prices,” Energy Economics, 25(3), pp.289- 301. [https://doi.org/10.1016/S0140-9883(02)00110-X]
  • Avanijaa, J.(2021), “Prediction of house price using xgboost regression algorithm,” Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(2), pp.2151-2155. [https://doi.org/10.17762/turcomat.v12i2.1870]
  • Bojer, C. S., and Meldgaard, J. P.(2021), “Kaggle forecasting competitions: An overlooked learning opportunity,” International Journal of Forecasting, 37(2), 587-603. [https://doi.org/10.1016/j.ijforecast.2020.07.007]
  • Boone, T., Ganeshan, R., Hicks, R. L., and Sanders, N. R.(2018), “Can Google trends improve your sales forecast?,” Production and Operations Management, 27(10), pp.1770-1774. [https://doi.org/10.1111/poms.12839]
  • Breiman, L.(2001), “Random forests,” Machine Learning, 45, pp.5-32. [https://doi.org/10.1023/A:1010933404324]
  • Caldara, D., and Iacoviello, M.(2022), “Measuring geopolitical risk,” American Economic Review, 112(4), pp.1194-1225. [https://doi.org/10.1257/aer.20191823]
  • Chen, T., and Guestrin, C.(2016), “Xgboost: A scalable tree boosting system,” In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; August 13, 2016; San Francisco, California, USA, pp.785-794. [https://doi.org/10.1145/2939672.2939785]
  • Chou, Y. C., Chuang, H. H. C., Chou, P., and Oliva, R.(2023), “Supervised machine learning for theory building and testing: Opportunities in operations management,” Journal of Operations Management, 69(4), pp.643- 675. [https://doi.org/10.1002/joom.1228]
  • Chai, J., Guo, J. E., Meng, L., and Wang, S. Y. (2011), “Exploring the core factors and its dynamic effects on oil price: an application on path analysis and BVAR-TVP model,” Energy Policy, 39(12), pp.8022-8036. [https://doi.org/10.1016/j.enpol.2011.09.057]
  • EIA(Energy Information Administration, US) (2022), “SHORT-TERM ENERGY OUTLOOK”.
  • Faff, R. W., and Brailsford, T. J.(1999), “Oil price risk and the Australian stock market,” Journal of Energy Finance & Development, 4(1), pp.69-87. [https://doi.org/10.1016/S1085-7443(99)00005-8]
  • Gao, S., and Lei, Y.(2017), “A new approach for crude oil price prediction based on stream learning,” Geoscience Frontiers, 8(1), pp.183- 187. [https://doi.org/10.1016/j.gsf.2016.08.002]
  • Herrera, G. P., Constantino, M., Tabak, B. M., Pistori, H., Su, J. J., and Naranpanawa, A. (2019), “Long-term forecast of energy com- modities price using machine learning,” Energy, 179, pp.214-221. [https://doi.org/10.1016/j.energy.2019.04.077]
  • Jabeur, S. B., Mefteh-Wali, S., and Viviani, J. L. (2021), “Forecasting gold price with the XGBoost algorithm and SHAP interaction values,” Annals of Operations Research, pp. 1-21. [https://doi.org/10.1007/s10479-021-04187-w]
  • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., and Liu, T. Y.(2017), “Lightgbm: A highly efficient gradient boosting decision tree,” Advances in Neural Information Pro- cessing systems, 30.
  • Kraljic, P.(1983), “Purchasing Must Become Supply Management,” Harvard Business Review, September-October, pp.109-117.
  • Nagar, D., Raghav, S., Bhardwaj, A., Kumar, R., Singh, P. L., and Sindhwani, R.(2021), “Machine learning: Best way to sustain the supply chain in the era of industry 4.0,” Materials Today: Proceedings, 47, pp.3676- 3682. [https://doi.org/10.1016/j.matpr.2021.01.267]
  • Jurado, K., Ludvigson, S. C., and Ng, S.(2015), “Measuring uncertainty,” American Economic Review, 105(3), pp.1177-1216. [https://doi.org/10.1257/aer.20131193]
  • Li, R.(2010), “The Relationship among petroleum prices,” International Conference on Applied Economics-ICOAE , pp.459-463.
  • Miao, H., Ramchander, S., Wang, T., and Yang, D. (2017), “Influential factors in crude oil price forecasting,” Energy Economics, 68, pp.77- 88. [https://doi.org/10.1016/j.eneco.2017.09.010]
  • Simon, A., Deo, M. S., Venkatesan, S., and Babu, D. R.(2016), “An overview of machine learning and its applications,” International Journal of Electrical Sciences & Engineering, 1(1), pp.22-24.
  • Sharma, H., Harsora, H., and Ogunleye, B.(2024), “An Optimal House Price Prediction Algorithm: XGBoost,” Analytics, 3(1), pp.30-45. [https://doi.org/10.3390/analytics3010003]
  • Wei, G., Zhao, J., Feng, Y., He, A., and Yu, J.(2020), “A novel hybrid feature selection method based on dynamic feature importance,” Applied Soft Computing, 93, Article 106337. [https://doi.org/10.1016/j.asoc.2020.106337]
  • Younis, H., Sundarakani, B., and Alsharairi, M. (2022), “Applications of artificial intelligence and machine learning within supply chains: systematic review and future research direc- tions,” Journal of Modelling in Management, 17(3), pp.916-940. [https://doi.org/10.1108/JM2-12-2020-0322]
  • Zhang, Z., Bouri, E., Klein, T., and Jalkh, N.(2022), “Geopolitical risk and the returns and vola- tility of global defense companies: A new race to arms?,” International Review of Financial Analysis, 83, Article 102327. [https://doi.org/10.1016/j.irfa.2022.102327]

∙ 저자 임세환은 현재 연세대학교 경영대학 Operations Management 전공 석사과정에 재학 중이다. 공군사관학교 국방경영학과를 졸업하였으며, 공군 군수분야에 복무 중이다. 주요 연구 관심분야는 물류서비스품질, 공급사슬 리스크 관리, 운영관리에서의 예측이다.

∙ 저자 민순홍(Ph.D., Haslam College of Business, the University of Tennessee)은 연세대학교 경영대학 오페레이션/공급사슬 담당 교수이자 ESG/기업윤리연구센터 부센터장으로 일하고 있다. 주요 연구/강의 분야는 지속가능경영, 공급사슬관리 (SCM), B2B 관계 전략 등이다. International Journal of Logistics Management에 발표한 논문으로 ‘Emerald 최우수논문상’, 생산관리학회지에 발표한 논문으로 ‘현우 곽수일 생산관리 학술상’, 국제적으로 인용지수 높은 학술지 논문으로 ‘한국로지스틱스대상 학술상’ 및 연세대학교 우수업적교수상 연구부문 최우수상을 수상하였다.

∙ 저자 최경환은 방위사업청에서 근무중이다. 국방대학교를 졸업하였으며, 국방관리 석사와 군사 운영분석 박사를 취득하였다. 그후에는 방위사업청에서 F-35A, F-15K 등과 같은 전투기 사업을 담당해 왔고, 2020년부터 2년간 국방대학교에서 교수를 역임하기도 했다. 주요연구분야는 공급체인관리, 군수, 방위산업 등이다.