Machine learning models for predicting daily profitability in Mauritanian digital banking operations: a case study

Abstract

This article presents a case study on predicting daily profitability in Mauritanian digital banking operations using machine learning models. We utilized a dataset containing detailed information on daily operations to assess predictive models and predict profitability. The study assesses various machine learning models like logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), and multi-layer perceptron classifier (MLPClassifier), in order to identify the most precise model for predicting daily profitability. A systematic approach guides the analysis of banking transactions by performing detailed preprocessing operations which include type conversions, feature selection and missing value management. The dataset receives systematic partitioning into three parts for training, validation and testing to establish model reliability. LR had a recall rate of 99% and an F1-score of 99%, SVM had a recall rate of 53% and an F1-score of 54%, KNN had a recall rate of 96% and an F1-score of 95%, and MLPClassifier had a recall rate of 94% and an F1-score of 97%. The findings show that the LR model performed better than the other models in terms of both recall and F1-score. Future research will investigate both deep learning approaches and hybrid models to enhance prediction accuracy.