This research is aimed at establishing the forecast and analysis diagnosis models for competitiveness of logistics enterprise through integrating a real-valued genetic algorithm to determine the optimum parameters and SVM to perform learning and classification on data. The result of the proposed GA-SVM can satisfy a predicted accuracy of up to 95.56% for all the tested logistics enterprise competitive data. Notably, there are only 12 influential feature included in the proposed model, while the six features are ordinary and easily accessible from National Bureau of Statistics. The proposed GA-SVM is available for objective description forecast and evaluation of a logistics enterprise competitiveness and stability of steady development. © Springer-Verlag Berlin Heidelberg 2013.
CITATION STYLE
Ding, N., Li, H., & Wang, H. (2013). Analysis and prediction of logistics enterprise competitiveness by using a real GA-based support vector machine. In LISS 2012 - Proceedings of 2nd International Conference on Logistics, Informatics and Service Science (pp. 267–272). https://doi.org/10.1007/978-3-642-32054-5_40
Mendeley helps you to discover research relevant for your work.