Hybrid PCA-ANFIS approach and Dove Swarm Optimization for predicting Financial Distress

In this study, an Adaptive Neuro Fuzzy Inference System (ANFIS) based on Principal Component Analysis (PCA) is proposed for predicting the financial distress of companies. This system not only has the ability to adapt and learn, but also reduces the error, because it avoids additional parameters when input variables are too high. In order to confirm the effectiveness of this model, 181 listed companies in the Tehran Stock Exchange (905 companies-years) were selected by using systematic samples from 2011 to 2015, which 58 of those were distressed and 847 companies-years were healthy. These companies were randomly divided into two sets: a training set for designing model and a check set for validating the model. The results of the research show that the Adaptive Neuro Fuzzy Inference System based on Principal Component Analysis is capable for predicting the financial distress of companies accepted in Tehran Stock Exchange and when the proposed model is combined with Dove Swarm Optimization metaheuristic algorithm, Reducing the error value increases the accuracy of the model. Therefore, it can be seen that the use of a complementary algorithm can increase the predictability of the PCA-ANFIS model.