基于数据挖掘的内幕操纵行为甄别研究  

Discrimination on Insider manipulation With Data Mining Methods

作　　者：张宗新[1] 沈正阳 

机构地区：[1]复旦大学金融研究院,上海200433 [2]东北证券研究所,上海200002

出　　处：《管理工程学报》2008年第2期102-106,共5页Journal of Industrial Engineering and Engineering Management

基　　金：国家自然科学基金资助项目(70303006);国家社会科学基金资助项目(06CJY038)

摘　　要：本文以国内证券市场发生的内幕操纵股票为样本,以股票的超额收益、波动性、流动性以及贝塔系数等市场反应指标为研究变量,借鉴数据挖掘的思想,采纳Logistic模型、决策树模型和神经元网络模型对内幕操纵行为进行了甄别,并对模型的效果作了对比分析。This study is base on manipulated stocks in Chinese securities market and presents the logistic, decision tree and neural network models to identify the manipulated stocks with the use of data-mining thoughts on market＇s reaction characteristics, mainly including abnormal return, volatility, liquidity. And it makes a comparison among the three ones.

关 键 词：内幕操纵 LOGISTIC模型 决策树 神经元网络 

分 类 号：F830[经济管理—金融学]