All Issue

2020 Vol.38, Issue 3 Preview Page

Article

Forecasting the Daily Demand of Air Cargo Using Data Mining with CHAID Approach

Datamining 기법을 활용한 일별 항공화물 수요 예측

Kyung-Chang MIN1
Hun-Koo HA2*
민 경창1
하 헌구2*
1Ph.D. Program, Graduate School of Logistics, Inha University and Senior Researcher, Lotte Logistics Research Institute, Lotte Global Logistics, Seoul 04257, Korea
2Professor, Graduate School of Logistics, Inha University, Incheon 22212, Korea
1인하대학교 물류전문대학원 박사과정 및 롯데물류연구소 책임연구원
2인하대학교 물류전문대학원 교수
* Corresponding Author
June 2020. pp. 190-207
PDF XML Citation
Abstract

WTO 체제 출범 이후 급격하게 증가한 항공화물에 대한 수요는 최근 E-commerce와 Cross-Border Trade의 폭발적인 성장에 따라 향후 더욱 증가할 것으로 예상된다. 항공화물에 대한 수요가 증가함에 따라 항공화물에 대한 정확한 수요예측의 필요성 역시 증가하고 있다. 그러나 기존 항공수요와 관련된 연구들은 주로 여객을 대상으로 진행되어 왔다. 화물을 대상으로 한 연구의 경우 주로 중장기 경영전략, 인프라 투자 등을 목적으로 하는 장기적인 관점의 예측에 관한 것이 다수이다. 본 연구는 항공사, 공항 등의 세부 운영전략 수립에 실질적인 도움을 줄 수 있는 일단위 항공화물 수요예측 모형을 개발하고 제안하는데 그 목적이 있다. 본 연구에서는 인천국제공항에서 출발하는 K항공사의 일별 화물 물동량을 대상으로 공휴일 변수와 의사결정나무 가운데 하나인 CHAID 방법론을 활용하여 일별 물동량 예측 모형을 개발하였다. 예측모형은 총 2단계를 통해 개발되었다. 첫 번째 단계에서는 주차별 공휴일 정보와 ARIMA 방법론을 통해 도출한 주차별 물동량 예측치를 설명변수로 하는 나무모형을 통해 주차별 물동량을 예측하였다. 두 번째 단계에서는 앞서 도출한 주차별 항공화물 물동량 예측치와 주차 및 일별 공휴일 정보를 바탕으로 최종 일단위 예측모형을 개발하였다. 본 연구에서 개발한 예측모형을 바탕으로 향후 56일간의 예측정확도를 검증한 결과 일평균 93.9% 이상의 높은 정확도를 나타냈다. 이는 대표적인 시계열 방법론인 ARIMA 모형을 통한 예측 정확도 대비 일평균 8.6% 이상 높은 수준임을 확인하였다. 또한 일반적인 수요예측의 특성과 달리 예측시점으로부터의 시차와 상관없이 꾸준하게 높은 정확도를 유지한다는 점을 확인할 수 있었다. 더불어 특정 시점이 아닌 20개 시점으로 시점을 옮겨가며 예측한 결과물에서도 일평균 91.2%의 정확도를 보이며 예측 모형으로서의 가치를 확인하였다. 이에 본 연구가 향후 항공화물의 일단위 수요예측에 도움이 되길 바라며, 나아가 보다 다양한 분야의 일단위 수요예측에 활용될 것으로 기대된다.

키워드
항공화물수요
CHAID
일별 예측
데이터마이닝
수요예측

Since the WTO was launched in 1995, Air cargo demand has risen sharply. It is expected to grow further on the explosive growth of E-commerce and Cross-Border trade in recently. As air cargo demand increases, the importance and needs for the forecasting of air cargo demand is increasing as well. Most of previous researches has been focussed on passenger part. In the case of researches on the forecasting of air cargo demand, the majority of researches are conducted quarterly or yearly forecasting to apply for establishment of mid-/long-term strategies, and an investment plan for an airport. The purpose of this paper is to develope the daily air cargo forecasting model that is able to help players in aviation, airlines, airports, etc., establish detailed operational strategies. In this paper, Chi-squared automatic interaction detection methodology is used to develop the forecasting model. The forecasting model is developed through two steps. At the first step, the weekly volume of air cargo is predicted by using CHAID methodology based on predict value from autoregressive integrated moving average and holiday information. At the second step, the final model which is the daily air cargo demand forecasting model is developed based on the weekly forecasting result from the first step, and holiday information by CHAID method as well. Based on the forecasting model developed in this paper, the daily cargo volumes for the next 56 days are predicted and the forecasting accuracy for each day is 93.9% which is 8.6% point higher than the forecasting accuracy for ARIMA model. It was noted that, unlike the characteristics of general demand forecasts, the high forecasting accuracy is maintained regardless of time lag from the forecasting point. And the result of the forecasting by shifting the forecasting point to 20 point, the forecasting accuracy for each dais is 91.2%, is high as well. The research finding shows the forecast model of this paper is worth to use as a daily forecasting model. It is expected that this paper will help to forecast the daily air cargo demand, and will further be used to forecast daily demand in more diverse area.

Keywords
air cargo demand
CHAID
daily forecasting
data mining
demand forecasting
References
1 
Amin S. H., Zhang G., Akhtar P. (2016), Effects of Uncertainty on a Tire Closed-loop Supply Chain Network, Expert Systems with Applications, 73, 82-91.
10.1016/j.eswa.2016.12.024
2 
Chen S. C., Kuo S. Y., Chang K. W., Wang. Y. T. (2012), Improving the Forecasting Accuracy of Air Passenger and Air Cargo Demand: The Application of Back-propagation Neural Networks, Journal of Transportation Planning and Technology, 35(3), 373-392.
10.1080/03081060.2012.673272
3 
Gharehgozli A. H., Yu Y., Koster R. D., Udding J. T. (2014), A Decision-tree Stacking Heuristic Minimising the Expected Number of Reshuffles at a Container Terminal, International Journal of Production Research, 2014, 52(9), 2592-2611.
10.1080/00207543.2013.861618
4 
Hartigan J. A. (1975), Clustering Algorithms, John Wiley and Sons (Newyork), 330-340.
5 
Jang J. M., Lee B. H., Ko J. H. (2019), Determinants of Commute Time Satisfaction : Focusing on the Residents of Gyeonggi Province, Journal of Air Transport Management, 37(4), 290-301.
10.7470/jkst.2019.37.4.290
6 
Kim J. C., Son H. G., Park J. S. (2019), A Study on International Air Demand Forecasting by ARIMA-Intervention Model, J. Korean Soc. Transp., 37(1), Korean Society of Transportation, 51-65.
10.7470/jkst.2019.37.1.051
7 
Liu C., Hu Z., Li Y., Liu S. (2017), Forecasting Copper Prices by Decision Tree Learning, Resources Policy, 52, 427-434.
10.1016/j.resourpol.2017.05.007
8 
Lo W. W. L., Wan Y., Zhang A. (2015), Empirical Estimation of Price and Income Elasticities of Air Cargo Demand: The Case of Hong Kong, Transportation Research Part A: Policy and Practice, 78, 309-324.
10.1016/j.tra.2015.05.014
9 
Min K. C., Jun Y. I., Ha H. K. (2013), Forecasting the Air Cargo Demand With Seasonal ARIMA Model: Focusing on ICN to EU Route, J. Korean Soc. Transp., 31(3), Korean Society of Transportation, 3-18.
10.7470/jkst.2013.31.3.003
10 
Repko M. G. J., Santos B. F. (2017), Scenario Tree Airline Fleet Planning for Demand Uncertainty, Journal of Air Transport Management, 65, 198-208.
10.1016/j.jairtraman.2017.06.010
11 
Shin H. J., Lee G. W. (2019), Factors Affecting Air Cargo Demand: Focus on Trade Volumes between South Korea and Intra-Asia, KOREA INTERNATIONAL COMMERCE REVIEW, 34(3), 191-214.
12 
Suryani E., Chou S. Y., Chen C. H. (2012), Dynamic Simulation Model of Air Cargo Demand Forecast and Terminal Capacity Planning, Simulation Modelling Practice and Theory, 28, 27-41.
10.1016/j.simpat.2012.05.012
13 
Wu P. J., Chen M. C., Tsau C. K. (2017), The Data-driven Analytics for Investigating Cargo Loss in Logistics Systems, International Journal of Physical Distribution & Logistics Management, 47(1), 68-83.
10.1108/IJPDLM-02-2016-0061
14 
Xu S., Chan H. K., Zhang T. (2019), Forecasting the Demand of the Aviation Industry Using Hybrid Time Series SARIMA-SVR Approach, Transportation Research Part E 122, 169-180.
10.1016/j.tre.2018.12.005
15 
Yu Z., Haghighat F., Fung B. C. M., Yoshino H. (2010), A Decision Tree Method for Building Energy Demand Modeling, Energy and Buildings, 42(10), 1637-1646.
10.1016/j.enbuild.2010.04.006
16 
Zhang A., Zhang Y. (2002), Issues on Liberalization of Air Cargo Services in International Aviation, Journal of Air Transport Management, 8(5), 275-287.
10.1016/S0969-6997(02)00008-X
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 38
  • No :3
  • Pages :190-207
  • Received Date :2020. 04. 01
  • Revised Date :2020. 04. 26
  • Accepted Date : 2020. 06. 04
  • DOI :https://doi.org/10.7470/jkst.2020.38.3.190
Journal Informaiton Agriculture and Life Sciences Research Institute Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • NRF
  • KOFST
  • crossref crossmark
  • crosscheck
  • crossref cited-by
  • crossref funder-registry
  • open access
  • orcid
  • ccl
Journal Informaiton Journal Informaiton - close