Risco de insolvência e sentimento textual bancário: uma análise dos bancos de capital aberto no Brasil

Abstract

This study aimed to analyze whether the textual sentiment explains the greater risk of insolvency of publicly held banks in Brazil, with a sample composed of 17 companies and 450 observations referring to the period from the fourth quarter of 2012, until the fourth quarter of 2019. The empirical strategy adopted is divided in three parts: the first consists of using the unsupervised algorithm k-means to classify banks according to their risk of insolvency, a new measure of bankruptcy probability was elaborated during this process. At this stage, it was observed that 66 observations were classified as high risk, and 384 as low risk, thus being a more rigorous metric than the Z-score, regarding the classification of banks with high risk of insolvency. Then, supervised machine learning methods naive bayes and random forest and the logit model were used to identify which of these statistical techniques is more robust for the prediction of the variable constructed in the previous step. From the confusion matrix and the accuracy criterion it was possible to identify that the logistic model presented the greatest predictive power. Finally, a third step was taken to assess whether textual sentiment, the real percentage change in Gross Domestic Product (GDP), capitalization, profitability, liquidity, and the size of these firms explain the risk of bank insolvency. The results show that banks with a higher probability of bankruptcy have a more optimistic textual feeling.