摘要
波罗的海运价指数一直受到航运与国际贸易界的高度关注,研究波罗的海运价指数的波动规律,探讨其发展变化趋势日益为人们所重视.当前对波罗的海运价指数的预测主要采用时间序列方法,这些方法计算过程复杂,而且适应性相对较弱.利用BP网络强大的非线性映射功能,建立了一个预测BFI走势的模型,分别从短期与中长期对波罗的海运价指数进行预测,并用实际数据进行了验证,结果表明,利用神经网络对BFI进行预测具有很高的预测精度.
Baltic Freight Index is highly regarded by maritime trade and international trade realm. The fluctuation rule of BFI is regarded increasingly. At present, the method in forecasting BFI is mostly time series model. But the complex calculation and low adaptability is its limitation. Utilizing the non-linear mapping function of BP neural networks, this paper creates a model to forecast BFI. The model forecasts BFI from short-term and medium-long-term angle. At last, the model is validated by practical data. The result indicates the high precision of this model.
出处
《大连海事大学学报》
CAS
CSCD
北大核心
2004年第3期45-47,共3页
Journal of Dalian Maritime University
