Comparative analysis of four classification models (Logistic, LDA, QDA, Naive Bayes) to predict loan acceptance. Evaluated the performance of the models using accuracy and precision metrics to define the best one. Build a model to accurately classify applicants as approved or rejected based on certain characteristics. This can help a bank improve the efficiency of loan approval, reducing the risk of bad loans and being able to offer customized loan options. Understand the connections between different independent variables and the dependent variable, with the goal of identifying the statistical model that best fits the objectives and evaluating its performance.
The classification models proposed and used are: • Logistic regression model • Linear discriminant analysis (LDA) • Quadratic discriminant analysis (QDA) • Naïve Bayes (NB)
Supported by appropriate diagnostic models such as: • Confusion Matrices • ROC Curves • AUC
Balancing techniques used: • Smote • Undersampling • Oversampling
-- Please note: Read the contents of the ‘Instructions and Informations’ file for information on the various files used and results obtained. --