랜덤 포레스트를 이용한 상하이발 해운 및 항공 운임 지수 간 영향 분석
Analysis of the Impact between Shanghai-Originated Shipping and Air Freight Indices using Random Forest
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구는 상하이발 미국 및유럽노선의해운운임지수(SCFI)와 항공 운임 지수(BAI) 간의 영향 관계를 파악하고자 하였다. 랜덤 포레스트 모델을 활용하여 2016년부터의 SCFI(상하이발 미서안, 미동안, 북유럽, 지중해)와 BAI(상하이발 북미, 유럽)의 상호 영향 관계를 분석하였다. 분석 결과, 해운 운임에서는 북유럽 SCFI와 지중해 SCFI가 가장 중요한 변수로 나타났으며, 항공 운임 지수인 BAI는 해운 운임에 미치는 영향이 상대적으로 낮았다. 반면, 항공 운임에서는 유럽 BAI와 미국 BAI 간의 상호 영향이 크며, 해운 운임 지수인 북유럽 SCFI와 지중해 SCFI가 항공 운임에 영향을 미치는 것으로 나타났다. 이는 글로벌 이벤트로 인한 해운 운임 변동 시 화물이 항공 운송으로 전환될 수 있음을 시사한다.
Abstract
This study aims to investigate the impact relationship between the Shanghai Containerized Freight Index (SCFI) and the Baltic Exchange Air Freight Index (BAI) on routes. Utilizing a Random Forest model, we analyzed the mutual influence between the SCFI (Shanghai to U.S. West Coast, U.S. East Coast, Northern Europe, and Mediterranean) and the BAI (Shanghai to North America and Europe) from 2016 onwards. The analysis results showed that in shipping freight rates, the Northern Europe SCFI and the Mediterranean SCFI emerged as the most significant variables, while the air freight index BAI had a relatively low impact on shipping freight rates. Conversely, in air freight rates, there was a strong mutual influence between the Europe BAI and the U.S. BAI, and the shipping freight indices—Northern Europe SCFI and Mediterranean SCFI—were found to affect air freight rates. This suggests that cargo may shift to air transport when shipping freight rates fluctuate due to global events.
참고문헌 (16)
- 전준우, "해운 운임 간 인과관계에 관한 연구", 융합정보논문지, 9(12), pp.47~53 (2019)
- 전준우, "COVID-19 상황을 고려한 Shanghai Containerized Freight Index 예측", 해운물류연구, 통권 : 112, pp.517~536 (2021)
- Bergstra, J., "Random search for hyper-parameter optimization", Journal of machine learning research, 13(2) (2012)
- Breiman, L., "Random forests", Machine Learning, 45(1), pp.5~32 (2001)
- Chen, S. C., "Improving the forecasting accuracy of air passenger and air cargo demand : The application of back-propagation neural networks", Transportation Planning and Technology, 35(3), pp.373~392 (2012)
- Hsu, C. W., "A Practical Guide to Support Vector Classification", Department of Computer Science, pp.2003
- Klindokmai, S., "Evaluation of forecasting models for air cargo", The International Journal of Logistics Management, 25(3), pp.635~655 (2014)
- Kupfer, F., "The underlying drivers and future development of air cargo", Journal of Air Transport Management, 61, pp.6~14 (2017)
- Munim, Z. H., "Forecasting container shipping freight rates for the Far East–Northern Europe trade lane", Maritime Economics & Logistics, 19(2), pp.106~125 (2017)
- Rožić, T., "Volatile freight rates in maritime container industry in times of crises", Applied Science, 12(17), pp.8452~ (2022)
- Saeed, N., "Forecasting container freight rates using the Prophet forecasting method", Transport Policy, 133, pp.86~107 (2023)
- Shackman, J., "The interrelationship between ocean, rail, truck, and air freight rates", Maritime Business Review, 6(3), pp.256~267 (2021)
- Vo, T. D., "The impact of covid-19 pandemic on the global trade", International Journal of Social Science and Economics Invention, 7(1), pp.1~7 (2021)
- Wang, W., "Freight rate index forecasting with Prophet model based on multi-dimensional significant events", Expert Systems with Applications, 249(A), pp.123451~ (2024)
- Yin, J., "Seasonality patterns in the container shipping freight rate market", Maritime Policy & Management, 45(2), pp.159~173 (2018)