A hybrid neural network model based an improved PSO and SA for bankruptcy prediction
Predicting firms failure is one of the most interesting subjects for investors and decision makers. In this paper, a bankruptcy prediction model is proposed based on Artificial Neural networks (ANN). Taking into consideration that the choice of variables to discriminate between bankrupt and non-bankrupt firms influences significantly the models accuracy and considering the problem of local minima, we propose a hybrid ANN based on variables selection techniques. Moreover, we evolve the convergence of Particle Swarm Optimization (PSO) by proposing a training algorithm based on an improved PSO and Simulated Annealing. A comparative performance study is reported, and the proposed hybrid model shows a high performance and convergence in the context of missing data.
Keywords: Artificial Neural Network, Particle Swarm Optimization, Simulated Annealing, Bankruptcy, Failure
Download Full-Text
ABOUT THE AUTHORS
Fatima Zahra Azayite
A computer science engineer and PhD student in National School for Computer Science and Systems analysis. Her principle research domains are machine learning, business intelligence and optimization algorithms. She currently works as a Data analyst in a central bank and has then years’ experience in Data analysis, Business Intelligence and statistics.
Said Achchab
A graduate of the Mohammedia School of Engineering with a PhD in Applied Mathematics and a university qualification in Business Intelligence, Saïd Achchab also followed the senior management cycle of ENCG Settat. He is currently Professor of Quantitative Finance, Business Intelligence and Change Management at ENSIAS as well as Director of the Continuing Education Center of this same school.
Fatima Zahra Azayite
A computer science engineer and PhD student in National School for Computer Science and Systems analysis. Her principle research domains are machine learning, business intelligence and optimization algorithms. She currently works as a Data analyst in a central bank and has then years’ experience in Data analysis, Business Intelligence and statistics.
Said Achchab
A graduate of the Mohammedia School of Engineering with a PhD in Applied Mathematics and a university qualification in Business Intelligence, Saïd Achchab also followed the senior management cycle of ENCG Settat. He is currently Professor of Quantitative Finance, Business Intelligence and Change Management at ENSIAS as well as Director of the Continuing Education Center of this same school.
