基于滑动窗DFNN的含有复杂条款认股权证定价模型  

Sliding Windowed DFNN Pricing Model of Warrants with Complex Terms

作　　者：孙彬[1] 李铁克[1] 

机构地区：[1]北京科技大学经济管理学院,北京100083

出　　处：《郑州大学学报（理学版）》2011年第4期104-109,共6页Journal of Zhengzhou University:Natural Science Edition

基　　金：国家自然科学基金资助项目;编号70771008;70371057

摘　　要：将Black-Scholes模型与动态模糊神经网络相结合,构建一种含有复杂条款的认股权证定价模型.通过设定一定长度的滑动窗来保持采用固定长度的数据进行模型结果参数调整,同时采用动态调整前提参数策略,确保定价模型的泛化能力.以我国权证市场中认股权证阿胶EJC1为例进行分析,结果表明,提出的定价模型与RBF模型相比准确性较高,并且对权证价格走势判断较为准确.A pricing model of warrants with complex terms was proposed based on dynamic fuzzy neural network（DFNN） and Black-Scholes model.In order to get optimized result-parameters of model with fixed-length time series data,a sliding window was set for DFNN.A dynamic adjustment approach of premise parameters was introduced to improve generalization ability of the model.Comparing with RBF pricing model,DFNN showed smaller deviation and higher accuracy in pricing EJiao EJC1.

关 键 词：认股权证定价 BLACK-SCHOLES模型 滑动窗口 动态模糊神经网络 

分 类 号：F830.91[经济管理—金融学]