Unit:
Speciality Business Administration, Analytics and Information SystemsLibrary of the Faculty of Economics and of the Faculty of Business Administration
Author:
Kontogiannidis Efthimios
Supervisors info:
Δρίβας Κυριάκος, Αναπληρωτής Καθηγητής, Τμήμα Οικονομικής Επιστήμης, Πανεπιστήμιο Πειραιώς
Original Title:
Data analysis techniques for customer churn prediction in banks
Translated title:
Data analysis techniques for customer churn prediction in banks
Summary:
The study examines predictive practices to identify when a customer is likely to leave a specific bank. Through data analysis and predictive modeling, the study focuses on how the bank can proactively detect potential customer departures and take actions to retain its clientele.
Main subject category:
Technology - Computer science
Keywords:
Machine learning, Banks, Classification Models, Logistic Regression (LG), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Synthetic Minority Over-sampling Technique(SMOTE)
