Método para la determinación de insolvencia financiera a partir de algoritmos de clasificación borrosa supervisada y no supervisada

Abstract

The objective of this research is to propose a method for the determination of financial insolvency from supervised and unsupervised fuzzy classification algorithms. The application and validation of the method is carried out in the economic sector of construction in Colombia, due to the high percentage of companies in bankruptcy for the years 2017 and 2018. The input variables of the method correspond to indicators or ratios financial statements of each one of the companies studied, according to its use and application to both the Colombian context and the specific economic sector. In the end, the results of the application of the method are validated and contrasted using machine learning techniques together with the results issued by the Colombian Superintendency of Companies and its report on the status of the companies under study. Based on the above, the advantages of the proposed method are established.