financial bankruptcy prediction using artificial neural network and firefly algorithms in companies listed in tehran stock exchange

By anticipating financial turmoil, it is possible to take the necessary precautions before financial distress occurs by managers and investors. this study compares two algorithms for predicting bankruptcy using an artificial neural network (ann) and neural network optimized metaheuristic firefly algorithm (fa). to run the test, initial values are first set for the network weights and biases. then, during optimization, the fa algorithm generates a population of different weights and biases. the conversion function used in the output layer is linear, and a non-linear sigmoid function is selected for the middle layer. to conduct this research, the data of 79 companies listed on tse from 2012 to 2015 were collected and analyzed statistically by backpropagation neural network and fa algorithms. the results show that fa, compared to ann predicted the companies’ bankruptcy much better. also, the fa algorithm maintains a good correlation between bankrupt and non-bankrupt companies, just like real data.