Banca de QUALIFICAÇÃO: MARCELIO JEFERSON MARTINS ALENCAR

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : MARCELIO JEFERSON MARTINS ALENCAR
DATE: 29/09/2025
TIME: 14:00
LOCAL: meet.google.com/tan-cujf-pmh
TITLE:

Churn Prediction Algorithms: A Comparative Approach using Machine Learning in the Telecommunications Industry

KEY WORDS:

Churn; telecommunications; machine learning; prediction; customer retention.

PAGES: 56
BIG AREA: Ciências Sociais Aplicadas
AREA: Administração
SUMMARY:

This study focuses on the analysis of customer Churn in the telecommunications sector, one of
the main challenges faced by organizations due to high competitiveness and the significant
costs of acquiring new consumers. The research aims to comparatively evaluate machine
learning algorithms applied to Churn prediction, seeking to identify which algorithms may
provide greater predictive accuracy, as well as to evaluate the potentially most influential
factors in customers’ cancellation decisions. For this purpose, the Telco Customer Churn
dataset available on Kaggle will be used, undergoing preprocessing, feature engineering, and
the application of predictive models such as XGBoost, Random Forest, LightGBM, and
CatBoost. The performance of the algorithms will be compared using statistical metrics such
as accuracy, precision, recall, F1-Score, and AUC. In addition, explainability techniques such
as SHAP and LIME will be employed to interpret the results and identify the most determinant
attributes in Churn behavior. It is expected that the findings of this research will contribute both
to academic advancement, by broadening the understanding of predictive modeling in business
contexts, and to managerial practice, by providing strategic insights for customer retention in
telecommunications companies.

COMMITTEE MEMBERS:
Presidente - DIEGO DE SOUSA GUERRA
Externo ao Programa - 3431335 - JAIR PAULINO DE SALES - UFCAExterno à Instituição - LUCAS LOPES FERREIRA DE SOUZA - UNIFOR
Externo à Instituição - LUIZ ALVES DA SILVA CRUZ NETO - UEVA
Externo à Instituição - VERONICA LIDIA PENALOZA FUENTES - UECE