No abstract

Purpose – In order to avoid enterprise crisis and cause the domino effect, which influences the investment return of investors, the national economy, and financial crisis, establishing a complete set of feasible financial early warning model can help to prevent the possibility of enterprise crisis in advance, and thus, reduce the influence on society and the economy. The purpose of this paper is to develop an efficient financial crisis warning model. Design/methodology/approach – First, the fruit fly optimization algorithm (FOA) is used to adjust the coefficients of the parameters in the ZSCORE model (we call it the FOA_ZSCORE model), and the difference between the forecasted value and the real target value is calculated. Afterward, the generalized regressive neural network (GRNN model), with optimized spread by FOA (we call it FOA_GRNN model), is used to forecast the difference to promote the forecasting accuracy. Various models, including ZSCORE, FOA_ZSCORE, FOA_ZSCORE+GRNN, and FOA_ZSCORE+FOA_GRNN, are trained and tested. Finally, different models are compared based on their prediction accuracies and ROC curves. Furthermore, more appropriate parameters, which are different from the parameters in the original ZSCORE model, are selected by using the multivariate adaptive regression splines (MARS) method. Findings – The hybrid model of the FOA_ZSCORE together with the FOA_GRNN offers the highest prediction accuracy, compared to other models; the MARS can be used to select more appropriate parameters to further improve the performance of the prediction models. Originality/value – This paper proposes a hybrid model, FOA_ZSCORE+FOA_GRNN which offers better performance than the original ZSCORE model.

In recent years, the global economic recession, followed by failure of business due to poor management, has resulted in a domino effect that occurred throughout the financial system. To avoid the expansion of loss, the issue of business failures should be seriously considered.In this paper, firstly, to reduce the time and space spent in our models learning and prediction, we use the data mining methods --stepwise regression, genetic algorithms and self-organizing map network for pre-processing data. Secondly, to match with the food searching behavior of the fruit fly, we modify Pan's optimization algorithm to a three-dimension space for the General Regression Neural Network (FOAGRNN), then, compared it with the Backpropagation Neural Network, Genetic Programming, General Regression Neural Network (GRNN),and the traditional Least Square method for financial distress forecasting models. Finally, through a substantial number of experiments, we realized that if we wanted to study the company's financial crisis early warning, in addition to considering the company's financial variables, corporate governance variables should not be neglected. Besides, we also found that our modified 3D-FOAGRNN outperformed the General Regression Neural Network, Genetic Programming, Backpropagation Neural Network and the Least Square method in terms of forecasting accuracy.

No abstract