文章基本信息

标题：PARTICLE SWARM OPTIMIZATION AND SIMULATED ANNEALING TO DESIGN BANKRUPTCY PREDICTION NEURAL NETWORK
本地全文：下载
作者：FATIMA ZAHRA AZAYITE ; SAID ACHCHAB
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2019
卷号：97
期号：23
页码：3462-3474
出版社：Journal of Theoretical and Applied
摘要：Bankruptcy prediction models are one of the most interesting subjects in financial engineering research, especially for investors and creditors. In this paper, the Artificial Neural Network is explored as a powerful tool to predict firms� failure. However, defining the appropriate topology with a suitable set of parameters can be treated as an optimization problem In this study, we investigate the use of Particle Swarm Optimization and Simulated Annealing to develop a performant learning algorithm. The proposed learning algorithm uses an evolved Particle Swarm Optimization algorithm to ameliorate the convergence of the standard algorithm and Simulated Annealing to escape from local minima. Moreover, the leaning algorithm evolves at the same time the number of hidden neurons and the weight values to design the optimum topology. A comparative performance study with Multiple Discriminant Analysis as well as Classification and Regression Tree is reported. The results showed that the proposed model performs better in predicting firms� Bankruptcy.
关键词：Particle Swarm Optimization; Simulated Annealing; Artificial Neural Networks; Machine Learning; Bankruptcy