【摘要】 在Delphi法数据统计处理过程中,成员权值主要根据成员的经历、职务、年龄和自我评定等情况来确定,易导致方案加权平均值及方差计算不准确,大大影响Delphi法的精度和效率。为提高Delphi法的精度和效率,论文提出了基于BP神经网络的方案加权平均值计算模型,使成员权值分配与其决策预测结果直接相关,减少了人为不正确因素对权值分配的影响,使权值分配较为客观,并且权值分配还具有动态的自学习功能,具有一定的智能性。该计算模型被成功应用于股票上市公司经营业绩综合评价排序。更多还原

【Abstract】 Member’s weight in the traditional Delphi method is mainly determined by his experiences,position,age and his self evaluation etc,It is easy to lead to the inaccuracy of calculating additive weight average and variance,the low calculation precision and the low efficiency.In order to improve the calculative precision and efficiency of the traditional Delphi method,the calculative model of solution additive weight average based on BP artificial neural network is pro-posed.The calculation model has been successfully applied to comprehensively evaluate and sort operational results of stock listed companies of China.更多还原