基于BP神经网络的二手船价格评估研究

二手船价格是买卖二手船决策过程中非常关键的因素。为了准确地估算二手船价格,利用BP神经网络的高度非线性运算能力以及通过学习样本数据即可对事物复杂内在规律进行精确计算的特点,将BP神经网络应用于二手船价格的估算。利用从克拉克松获取的2009年到2012年120个灵便型干散货船交易数据,建立了基于船龄、船舶载重吨(DWT)、新造船价格和一年期期租费率的BP神经网络模型,网络输出结果与二手船实际交易价格的相对误差率在10%以内。

Study on Calculating Second-hand Ship Price Based on BP Neural Network

A second-hand ship price is an important factor in the process of decision making to purchase of second-hand ships. In this paper, BP neural network is used to calculate the second-hand ship prices for its significant capacity to non-linearity simulate and grasp the inherent laws by self-study. By applying the 120 deals of second-hand handy-size bulkers from 2009 to 2011 from Clarkson, the BP neural network model based on the age of the vessel, DWT, new-building price and one year time charter rate is proved to be scientific and reasonable in calculating second-hand ship prices with relative error rate of output of network and actual prices within 10%.