【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。更多还原

【Abstract】 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.更多还原