Legal Judgment Prediction in the Context of Energy Market using Gradient Boosting

• Main Authors: Franca, Joao V. F., Boaro, Jose M. C., dos Santos, Pedro T. C., Henrique, Fernando, Garcia, Venicius, Manfredini, Caio, Junior, Domingos A. D., de Oliveira, Francisco Y. C., Castro, Carlos E. P., Braz Junior, Geraldo, Silva, Aristofanes C., Paiva, Anselmo C., de Oliveira, Milton S. L., Moreira e Moraes, Renato U., Alves, Erika W. B. A. L., Sobral Neto, Jose S.
• Format: Conference Proceeding
• Language: English
• Subjects: Companies; Encoding; Feature extraction; Law; Legal Judgment Prediction; Machine Learning; Prediction algorithms; Quality of service; TPE; XGBoost
• ISSN: 2577-1655
• DOI: 10.1109/SMC42975.2020.9283297

A recurring problem for energy supply companies is the guarantee of the quality of services, which is regulated in many cases. Even so, there are many lawsuits against energy distribution companies, for several reasons, increasing the operating costs of these companies, in many situations with cases that could be resolved via negotiation. This work proposes a method to predict legal judgment outcome regarding the chance of being won or lost by the company. The idea is to understand in which lawsuits more effort should be made to negotiate with the court. The methodology is divided into five stages: feature extraction, sampling with Borderline SMOTE, feature encoding with Target Encoding, classification with XGBoost, and evaluation. The proposed method was evaluated in a database with more than seventy thousand lawsuits, with different outcomes and types, reaching an accuracy of 78.13%, F1 of 74.34%, and AUC of 77.59%.