Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Forecasting of Iron Ore Prices using Machine Learning

머신러닝을 이용한 철광석 가격 예측에 대한 연구

  • 이우창 (계명대학교 경영정보학과) ;
  • 김양석 (계명대학교 경영정보학과) ;
  • 김정민 (계명대학교 경영정보학과) ;
  • 이충권 (계명대학교 경영정보학과)
  • Received : 2020.02.10
  • Accepted : 2020.04.14
  • Published : 2020.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The price of iron ore has continued to fluctuate with high demand and supply from many countries and companies. In this business environment, forecasting the price of iron ore has become important. This study developed the machine learning model forecasting the price of iron ore a one month after the trading events. The forecasting model used distributed lag model and deep learning models such as MLP (Multi-layer perceptron), RNN (Recurrent neural network) and LSTM (Long short-term memory). According to the results of comparing individual models through metrics, LSTM showed the lowest predictive error. Also, as a result of comparing the models using the ensemble technique, the distributed lag and LSTM ensemble model showed the lowest prediction.

철광석의 가격은 여러 국가와 기업들의 수요와 공급에 따라서 높은 변동성이 지속되고 있다. 이러한 비즈니스 환경에서 철광석의 가격을 예측하는 것은 중요해졌다. 본 연구는 머신러닝 기법을 이용하여 철광석이 거래되는 시점으로부터 한 달 전에 철광석 거래가격을 미리 예측하는 모형을 개발하고자 하였다. 예측 모형은 시계열 데이터를 활용한 예측 방법론으로 많이 활용되고 있는 시차분포 모형과 다층신경망 (Multi-layer perceptron), 순환신경망 (Recurrent neural network), 그리고 장단기 기억 네트워크 (Long short-term memory)와 같은 딥 러닝(Deep Learning) 모형을 사용하였다. 측정지표를 통해 개별 모형을 비교한 결과에 따르면, LSTM 모형이 예측 오차가 가장 낮은 것으로 나타났다. 또한, 앙상블 기법을 적용한 모형들을 비교한 결과, 시차분포와 LSTM의 앙상블 모형이 예측오차가 가장 낮은 것으로 나타났다.

Keywords

References

  1. Chung, E. C., and Lee, C. M. (2018). Determinants of Chonsei Deposit to Housing Sales Price Ratio Based on Rental Housing Market Equilibrium Condition: Focused on Housing Price Volatility, Journal of the Korea Real Estate Analysts Association, 24(4) 5-20. https://doi.org/10.19172/KREAA.24.4.1
  2. Choi, H., Moon T., Jung, D. H., and Son, J. E. (2019). Prediction of Air Temperature and Relative Humidity in Greenhouse via a Multilayer Perceptron Using Environmental Factors, Protected Horticulture and Plant Factory, 28(2), 95-103. https://doi.org/10.12791/KSBEC.2019.28.2.95
  3. Chu, J. M., and Kong, M. K. (2015). Changes and Implications of Steel Export Structure in Korea, China and Japan, POSRI Issue Report, 2015(9), 1-10.
  4. Granger, C. W. J. (1969). Investigating Causal Relations by Econometric Models and Cross-spectral Methods, Econometrica, 37(3), 424-438. https://doi.org/10.2307/1912791
  5. Huh, J. S. (2018). Mid-term Global Iron Ore Market and Purchasing Issue Analysis and Implications, POSRI Issue Report, 2018(8), 1-10.
  6. Hong, H. K. (2009). A Study on the Apartment Price Model using Neural Network Model, Proceedings of the Spring Conference on Korea Society of Industrial Information Systems Research, 220-226, Korea.
  7. Jung, H. J., Yoon, J. S., and Bae S. H. (2017). Traffic Congestion Estimation by Adopting Recurrent Neural Network, Journal of Korea Intelligent Transport Systems, 16(6), 67-78. https://doi.org/10.12815/kits.2017.16.6.67
  8. Jang, W., (2018). Factors Determining China's Iron Scrap Export Volume, POSRI Issue Report, 2018(12), 1-9
  9. Kim, K. M., and Kim, D. H. (2018). A Causality Test on Hairtail Prices among Import and Domestic Markets Using a Vector Error Correction Model (VECM), Journal of the Ocean and Polar Research, 40(1), 49-58.
  10. Kim, I. C., and Kim D. Y. (2001). A Study on the Features for Building Korea Digit Recognition System Based on Multilayer Perceptron, Journal of the Korea Industrial Information Systems Research, 6(4), 81-88.
  11. Kim, S. S., and Hong, K. J. (2017). Development and Performance Analysis of Predictive Model for KOSPI 200 Index using Recurrent Neural Networks, Journal of the Korea Industrial Information Systems Research, 22(6), 23-29. https://doi.org/10.9723/JKSIIS.2017.22.6.023
  12. Kim, H., Tak, H., and Cho, H. G. (2019). Design of Photovoltaic Power Generation Prediction Model with Recurrent Neural Network, Journal of the Korean Institute of Information Scientists and Engineers, 46(6), 506-514.
  13. Kim, M. S. (2010). The Research on Liquidity and Issues of Steel Market in the Construction Industry, M. E. Thesis, Graduate School of Seoul Industry University, Seoul, Korea.
  14. Kang, K., and Kim, C. (1996). ATM Connection Admission Control Scheme Using Multilayer Perceptron, Journal of KISS(A): Computer Systems and Theory, 23(12), 1225-1237.
  15. Lee, W. C., Kim, J. M., and Lee, C. K. (2019a). A Study on the Factors Affecting the Price of Iron Ore, Proceedings of the Spring Conference on The Korea Society Management Information Systems, 102-106, Korea.
  16. Lee, D. G., Sun, Y. G., Kim, S. H., Sim, I., Hwang, Y. M., and Kim, J. Y. (2019b). Comparison of Power Consumption Prediction Scheme Based on Artificial Intelligence, Journal of The Institute of Internet, Broadcasting and Communication, 19(4), 161-167.
  17. Liu, J. (2012). A Comparative Study on the Competitiveness of Chinese Steel Industry against Korea and Japan, Ph. D. Thesis, Graduate School of Dong-Eui University, Busan, Korea.
  18. Lee, B., and Son, W. (2019). A Comparative Analysis of Structural Changes of Korea, China, and Japan in Product Space, Policy References in Korea Institute for International Economic Policy, 19(4), 1-99.
  19. Liu, J., and Han, K. (2012). A Study on the Trade Structure of Steel Industry between China and Japan, Journal of the Korean-Japanese Economic & Management Association, 56(0), 111-127.
  20. Lee, I. N. (2006). The Impact of Raw Material Price Increase on Domestic Prices: An Input-Output Analysis of Price Pass-through, Korea Association Of Public Policy, 21, 61-89.
  21. Lee, S., and Ryu, Y. U. (2017). Industrial Economic Growth and IT Investment: Is Economic Growth an Effect of IT Investment, or a Determinant of Decision-making for IT Investment, Journal of The Information Systems Review, 19(1), 185-202.
  22. Lee, S. M., Sun, Y. G., Lee, J., Lee D., Cho, E. I., Park D. H, Kim, Y. B., Sim, I., and Kim, J. Y. (2019). Short-term Power Consumption Forecasting Based on IoT Power Meter with LSTM and GRU Deep Learning, Journal of The Institute of Internet, Broadcasting and Communication (IIBC) , 19(5), 79-85.
  23. Malanichev, A. G., and Vorobyev P. V. (2011). Forecast of Global Steel Prices, Studies on Russian Economic Development, 22(3), 304-311. https://doi.org/10.1134/S1075700711030105
  24. Moon, J., Park, S., and Hwang, E. (2019). A Multilayer Perceptron-Based Electric Load Forecasting Scheme via Effective Recovering Missing Data, Journal of the Korea Information Processing Society, 8(2), 67-78.
  25. Makridakis, S., and Winkler R. L. (1983). Averages of Forecasts: Some Empirical Results, Journal of the Management Science, 29(9), 987-996.
  26. Nam, D. Y. (2016). A Study on Early Warning System of Iron Ore Price based on Signal Approach Model, Research in Chinese Studies, 76, 131-149.
  27. Nam, D. Y. (2018). A Study on Early Warning System of China Iron Ore Price Based on AI Models, China Academic Conference, 61, 215-232.
  28. Pustov, A., Malanichev, A., and Khobotilov I. (2013). Long-term Iron Ore Price Modeling: Marginal Costs vs. Incentive Price, Journal of the Resources Policy, 38(4), 558-567 https://doi.org/10.1016/j.resourpol.2013.09.003
  29. Pearson, M. H., Shin, Y., and Smith, R. J. (2001). Bounds Testing Approaches to the Analysis of Level Relationship, Journal of Applied Econometrics, 16, 289-326. https://doi.org/10.1002/jae.616
  30. Rhee, B. K. (2017). Effect of Economic Sanctions on Trade: Distributed Lag Analysis, Journal of the Korea International Commerce Review, 32(4) 399-413.
  31. Song, H. S. (2017). Comparison of Performance between MLP and RNN Model to Predict Purchase Timing for Repurchase Product, Journal of Information Technology Applications & Management, 24(1), 111-128. https://doi.org/10.21219/jitam.2017.24.1.111
  32. Silvey, S. D. (1969). Multicollinearity and Imprecise Estimation, Journal of the Royal Statistical Society, 31(3) 539-552. https://doi.org/10.1111/j.2517-6161.1969.tb00813.x
  33. Shin, S., Lee, M., and Song, S. K. (2018). A Prediction Model for Agricultural Products Price with LSTM Network, Journal of the Korea Contents Association, 18(11), 416-429. https://doi.org/10.5392/JKCA.2018.18.11.416
  34. Wu, J. Q., Wu, J. Q., and Chen, X. B. (2012). Import Iron Ore Price Forecasting based on PSO-SVMs Model, The 7th International Computer Science & Education Conference, Jul, 14-17, Melbourne, VIC, Australia, pp. 32-35.
  35. Won, D. H., and Yang, C. H. (2011). A Study on the Validity of Logistics Collaboration for Steel Exports and Imports-Focused on Trade with China and Japan, Korea Trade Research Association, 36(3), 321-342.