In this paper, considering the financial performance of China's listed companies as the dependent variable, a computational intelligence method based on genetic algorithms and discriminant analysis is employed to screen variables that influence financial performance and forecast the change of financial performance. Specifically, a new model based on genetic algorithms is developed to screen factors that influence financial performance of Chinese listed companies. The empirical results show that variables selected by genetic algorithms can predict financial performance well.

No abstract

No abstract

In order to forecast the corporate finance performance, we must choose the appropriate forecast method. The forecast model widely used at present lacks generalization ability and the accuracy is not approving. In this paper, we propose an improved version of support vector machines (named AdaBoost support vector machine) to forecast financial performance of Chinese listed companies. In the choice of kernel function of support vector machine, we compare forecast results for each kernel function and its associated parameters in order to identify the most appropriate forecasting model. The experiment results show that AdaBoost-support vector machine model with rbf kernel function behaves quite well than other methods (such as probabilistic neural network and decision tree model).

No abstract