Forecasting container throughput with big data using a partially combined framework

This study proposes a partially-combined forecasting framework for container throughput based on big data composed of structured historical data and unstructured data. Under the proposed framework, the structured data (the original time series) is firstly decomposed into linear component and nonlinear component. Seasonal auto-regression integrated moving average model (SARIMA) is adopted to capture and forecast the linear component, and a combined model, composed of least squares support vector regression (LSSVR) and artificial neural network (GP), is applied to modeling the nonlinear component. Next, unstructured data is analyzed by an expert system. With the synthesized expert judgment, the forecasts of linear and nonlinear components are integrated into a final forecast. For the illustration and verification purpose, an empirical study is conducted with the data of Qingdao Port. The results show that the model under the proposed framework significantly outperforms its competitive rivals.

[1]  Rustam M. Vahidov,et al.  Application of machine learning techniques for supply chain demand forecasting , 2008, Eur. J. Oper. Res..

[2]  Xin Tian,et al.  A TEI@I-Based Integrated Framework for Port Logistics Forecasting , 2009, 2009 International Conference on Business Intelligence and Financial Engineering.

[3]  Kin Keung Lai,et al.  Foreign-Exchange-Rate Forecasting with Artificial Neural Networks , 2007 .

[4]  Fong-Lin Chu,et al.  Analyzing and forecasting tourism demand with ARAR algorithm , 2008 .

[5]  Shrisha Rao,et al.  Air Cargo Demand Modeling and Prediction , 2014, IEEE Systems Journal.

[6]  Xiaohang Yue,et al.  Production , Manufacturing and Logistics Demand forecast sharing in a dual-channel supply chain , 2006 .

[7]  Gérard P. Cachon,et al.  Contracting to Assure Supply: How to Share Demand Forecasts in a Supply Chain , 2001, Manag. Sci..

[8]  Jussi T. S. Heikkilä,et al.  From supply to demand chain management: efficiency and customer satisfaction , 2002 .

[9]  Edward W. Davis,et al.  Extended Enterprise , 2003, Encyclopedia of Biometrics.

[10]  Gin-Shuh Liang,et al.  Application of fuzzy regression on air cargo volume forecast , 2008 .

[11]  M. Mazzocchi,et al.  Tourism demand for Italy and the business cycle , 2010 .

[12]  Daniel DeLaurentis,et al.  Development of network restructuring models for improved air traffic forecasts , 2010 .

[13]  Angappa Gunasekaran,et al.  Supply chain management: Theory and applications , 2004, Eur. J. Oper. Res..

[14]  Byron Gangnes,et al.  Modeling tourism: A fully identified VECM approach , 2009, International Journal of Forecasting.

[15]  Narjesse Teyssier How the consumer confidence index could increase air travel demand forecast accuracy , 2012 .

[16]  Yossi Aviv,et al.  The Effect of Collaborative Forecasting on Supply Chain Performance , 2001, Manag. Sci..

[17]  Ulrich Wilhelm Thonemann,et al.  Production, Manufacturing and Logistics Improving supply-chain performance by sharing advance demand information , 2002 .

[18]  Hong-jun Heng,et al.  Study of SVM-Based Air-Cargo Demand Forecast Model , 2009, 2009 International Conference on Computational Intelligence and Security.