Machine learning aplicado no problema de perdas com créditos de uma distribuidora de energia elétrica

Abstract

Estimated Losses on Doubtful Accounts (ELDA) in companies is an attractive field for investigation due to the percentage of profits it represents. The objective of this work is to find a machine learning model to predict on which day the customer will pay the energy bill in order to maximize the company’s profit. To evaluate the proposed methodology, experiments were carried out using real data from customer invoices. The results of the models were compared with each other and statistical analysis was performed to verify if there is a significant difference between them. The results achieved indicate that the application of the proposed modeling is promising.