基于模糊神经网络的航运运价指数预测  

Shipping freight index forecasting based on fuzzy neural network

作　　者：董良才[1] 黄有方[1] 胡颢[1] 

机构地区：[1]上海海事大学物流工程学院,上海200135

出　　处：《大连海事大学学报》2010年第4期31-34,共4页Journal of Dalian Maritime University

基　　金：上海市优秀学科带头人项目(08XD14019);上海市教委支出预算项目(2008086)

摘　　要：为航运市场的参与者提供准确和高效的预测模型及决策支持,以BDI指数为研究对象,分析其时间序列数据所包含的内部信息和统计特征,采用模糊数理技术与神经网络技术,为BDI指数建立模糊神经网络模型.相比传统神经网络,模糊神经网络对于BDI指数时间序列在预测能力上的表现更优.To provide an effective and accurate forecasting model and decision support for shipping market participants,taking Baltic Dry Index（BDI） as research object,the statistical tests on stationariness and nonlinearity of the BDI time series data were analyzed,and mathematical statistic method and neural network technique were used to set up an effective fuzzy neural network model.Comparing with the traditional neural network,the fuzzy neural network has better performance for prediction capability.

关 键 词：航运运价 波罗的海干散货指数(BDI) 预测 模糊神经网络 

分 类 号：F550.5[经济管理—产业经济]