RESUMO Esta pesquisa buscou analisar as variáveis que podem influenciar a falência das empresas. Durante vários anos, as principais pesquisas sobre falência reportaram as metodologias convencionais visando à sua predição. Em suas análises, a utilização de variáveis contábeis predominou maciçamente. Porém, ao aplicá-las, as variáveis contábeis eram consideradas homogêneas, ou seja, para os modelos tradicionais, presumia-se que em todas as empresas o comportamento dos indicadores era similar, ignorando a heterogeneidade entre elas. Observa-se, ainda, a relevância da crise financeira ocorrida no final de 2007, causando grande colapso financeiro mundial, tendo efeitos diferentes nos mais diversos setores e empresas. Nesse cenário, pesquisas que visam identificar problemas como a heterogeneidade entre as empresas e analisar as diversidades entre elas ganham relevância, haja vista que as características setoriais de estrutura de capital, porte, dentre outras, variam de acordo com as empresas. A partir disso, novas abordagens aplicadas à modelagem de previsão de falência devem considerar a heterogeneidade entre as empresas, buscando aprimorar ainda mais as modelagens utilizadas. Foram utilizadas a árvore e a floresta causais com dados contábeis trimestrais e setoriais de 1.247 empresas, sendo 66 falidas, das quais 44 depois de 2008 e 22 antes. Os resultados mostraram que existe heterogeneidade não observada quando se analisam os processos de falência das empresas, colocando em cheque os modelos tradicionais como, por exemplo, análise discriminante e logit, dentre outros. Por conseguinte, com o elevado volume em dimensões, observou-se que pode haver uma forma funcional capaz de explicar a falência das empresas, porém essa não é linear. Destaca-se, ainda, que existem setores mais propensos a crises financeiras, agravando o processo de falência.
ABSTRACT This study sought to analyze the variables that can influence company bankruptcy. For several years, the main studies on bankruptcy reported on the conventional methodologies with the aim of predicting it. In their analyses, the use of accounting variables was massively predominant. However, when applying them, the accounting variables were considered as homogenous; that is, for the traditional models, it was assumed that in all companies the behavior of the indicators was similar, and the heterogeneity among them was ignored. The relevance of the financial crisis that occurred at the end of 2007 is also observed; it caused a major global financial collapse, which had different effects on a wide variety of sectors and companies. Within this context, research that aims to identify problems such as the heterogeneity among companies and analyze the diversities among them are gaining relevance, given that the sector-related characteristics of capital structure and size, among others, vary depending on the company. Based on this, new approaches applied to bankruptcy prediction modeling should consider the heterogeneity among companies, aiming to improve the models used even more. A causal tree and forest were used together with quarterly accounting and sector-related data on 1,247 companies, 66 of which were bankrupt, 44 going bankrupt after 2008 and 22 before. The results showed that there is unobserved heterogeneity when the company bankruptcy processes are analyzed, raising questions about the traditional models such as discriminant analysis and logit, among others. Consequently, with the large volume in terms of dimensions, it was observed that there may be a functional form capable of explaining company bankruptcy, but this is not linear. It is also highlighted that there are sectors that are more prone to financial crises, aggravating the bankruptcy process.