Determining financial indicators with rough sets based feature selection techniques – a review

Abstract

Better prediction and classification in determining company's performance are major concern for practitioners and academic research, due to its importance in giving useful information for stock-holder and its potential investors in making a good decision regarding investment. The firm's performance can be analyzed based on financial indicators as reported in company's annual report, balance sheet, and income statement. As a result, many financial indicators or ratios need to be considered for classifying the performance of each firm. Therefore, this study will investigate and identify financial indicators that will give the most significance impact in predicting company's performance. A hybrid of soft computing and hard computing techniques, i.e., rough set method and statistical approach will be explored for pre-analysis and post-analysis in identifying the most significant indicators for the classification of the company's performance. This study will also investigate the impact of employing difference indicators in predicting high performance and failure of the firms.