Feature Selection Optimization Model for Business Risk Assessment Model

Abstract

Financial risk assessment becomes a hot research topic among financial firms or companies to assess the financial status and thereby avoid future crises. Earlier studies have focused on statistical models for the assessment of financial risks and the recently developed machine learning (ML) models find useful to improve the assessment performance. In this aspect, this study introduces a novel Butterfly Optimization based Feature Selection with Classification Model for Financial Risk Assessment (BOFS-CFRA) technique. The proposed BOFS-CFRA technique involves pre-processing at the primary stage to get rid of unwanted data. In addition, K-means clustering approach is developed to group the financial data into clusters. Then, the BOFS technique is applied to choose the subset of features from the clustered data. Finally, the classification of financial risks takes place by the use of functional link neural network (FLNN). In order to ensure the enhanced performance of the BOFS-CFRA technique, a series of simulations were carried out and the results are inspected under various measures. The simulation outcome portrayed the supremacy of the BOFS-CFRA technique over the other financial risk assessment models in terms of several performance measures.