AUTHOR=Torres Gabriel de Oliveira , Guterres Marcelo Xavier , Celestino Victor Rafael Rezende 

TITLE=Legal actions in Brazilian air transport: A machine learning and multinomial logistic regression analysis

JOURNAL=Frontiers in Future Transportation

VOLUME=Volume 4 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/future-transportation/articles/10.3389/ffutr.2023.1070533

DOI=10.3389/ffutr.2023.1070533

ISSN=2673-5210

ABSTRACT=In Brazil, one of the costs that most harm airlines is the high number of lawsuits filed against them. It is a problem that can affect its operations, reduce the entry of new competitors and create legal uncertainty in the country. This work seeks to highlight the factors which contribute the most to the rise of judicial indemnities, discuss the most relevant factors and identify the best technique to predict the indemnified values. The objective is to provide subsidies for airlines to mitigate the number of legal actions with the aid of machine learning models. This research contributes by discussing one of the most relevant subjects in Brazilian air transport and comparing the machine learning models performance. The study is based on lawsuits between 2016 and 2021 using the companies' data. The performances of Naive Bayes, Random Forest, Support Vector Machines and Multinomial Logistic Regression models are evaluated through the accuracy, area under the ROC curve and confusion matrix. The results showed better predictive power for Random Forest and Logistic Regression. The latter showed that flight delays, cancellations and airline fault have negative effects on the indemnities. The above-average compensation is a tendency in some states, being the moral damage awarded to customers, the main cause of higher compensation.