|標題：Integration of Evolutionary Computing and Equity Valuation Models to Forecast Stock Values Based on Data Mining|
|作品名稱||Integration of Evolutionary Computing and Equity Valuation Models to Forecast Stock Values Based on Data Mining|
|著者||Chang, Ying-Hua; Wang, Shih-Chin|
|著錄名稱、卷期、頁數||Asia Pacific Management Review=亞太管理評論 18(1), pp.63-78|
|摘要||Fundamental analysis uses financial data to assess firm value. For the majority of investors, financial reports in the form of fundamental analysis are the key reference; investors can use quarterly financial reports issued by enterprises to know enterprise operating performance and financial situation. Thus even though investors do not participate in enterprise operations, the availability of open information allows them to evaluate enterprise earnings and associated risks, and thus to predict enterprise market value.
This study applies evolution strategies combined with the artificial neural network and Ohlson model to construct the evaluation module. However, for completeness, the Ohlson model includes corporate governance and other variables in the non-accounting information, to discuss the variable structure and data range in which the Ohlson model can optimize firm value.
Because many factors influence firm value and the relationship among those factors are nonlinear, common traditional statistical methods have difficulty finding solutions. Therefore, this essay applies the artificial intelligence method, which through the good learning ability of artificial neural networks and the good optimization ability of the evolution strategies, tries to identify the characteristics and their ranges of three types of corporations and easily value the related stock.
This study uses the calculated firm value to identify the optimal range of variables in the rules, their accuracy get over 90%, and thus to maximize firm value. This approach can not only provide a reference for enterprise management, but also one for investors to use in analyzing corporate market value.
|關鍵字||Evolution strategies; Artifical neural networks; Data mining; Corporate government; Ohlson model|