Analysis of credit risk faced by public companies in Brazil: an approach based on discriminant analysis, logistic regression and artificial neural networks

Abstract

The aims of the present article are to identify the economic-financial indicators that best characterize Brazilian public companies through credit-granting analysis and to assess the most accurate techniques used to forecast business bankruptcy. Discriminant analysis, logistic regression and neural networks were the most used methods to predict insolvency. The sample comprised 121 companies from different sectors, 70 of them solvent and 51 insolvent. The conducted analyses were based on 35 economic-financial indicators. Need of working capital for net income, liquidity thermometer, return on equity, net margin, debt breakdown and equity on assets were the most relevant economic-financial indicators. Neural networks recorded the best accuracy and the Receiver Operating Characteristic Curves (ROC curve) corroborated this outcome.

Application of Canonical Variate Analysis to Compare Different Groups of Food Industry Companies in Terms of Financial Liquidity and Profitability

“…After making predictions for a single financial ratio and assuming a uniform dataset structure, the advantage of this method is an indication of the direction and strength of independent variables that affect the dependent variable [35,76]. In addition, some methods develop a linear model, such as Logit and Probit application modeling [77,78] or artificial neural networks [79,80], which improve the overall prediction accuracy. On the other hand, the disadvantage of this approach is the assumption that the variables from which the explanatory variable values are estimated are independent.…”

Informative Transparency on Entrepreneurship by Spanish Local Governments

“…In order to achieve the second objective of this study, and once the literature review had been carried out, the explanatory variables defined in previous sections were considered, as shown in Table 3 [35,59]. We proceed to carry out an explanatory analysis in order to identify the factors that significantly influence the disclosure of information on entrepreneurship in the town councils of Spanish capitals.…”

Modelación de la probabilidad de incumplimiento y cálculo de la perdida catastrófica en una institución financiera en Colombia

“…Siguiendo a Do Prado et al (2019), el modelo Logit binario tiene las siguientes condiciones establecidas en la ecuación 2:…”

“…Finalmente, los resultados obtenidos en este trabajo ratifican lo encontrado en los estudios de Do Prado et al (2019), Grundke, Pliszka y Tuchscherer (2019), Russo, Lagasio, Brogi y Fabozzi (2020) y Sariev y Germano (2020).…”