Regresar

Classification system for corporate reputation based on financial variables

Abstract:

The most important external assessment for companies is reputation, which is very difficult to calculate since its characterization may require a large number of qualitative and quantitative data. This study presents a comparison of different corporate reputation classification systems based on financial variables. Initially, a database was constructed using data from the Corporate Reputation Business Monitor and the Business Information and Reporting System of the Colombian Superintendence of Companies. The records were labeled as high and low. Then, a relevance analysis was carried out, using linear discriminant analysis. Four classifiers (ANFIS, K-NN, F-NN, and SVM-PSO) were compared to categorize the reputation, achieving a performance of 94% accuracy, which allowed to demonstrate the discriminant capacity of the financial variables to classify the reputation.