Financial Distress Prediction in Kenyan Saccos: A Comparative Analysis of Machine Learning Models

Financial distress prediction is crucial for assessing the economic health of any organization or nation; as a whole. This research focuses on developing a robust machine learning model to predict financial distress in Kenyan Savings and Credit Cooperative Organizations (SACCOs). Notably, this is one of the first studies to explore financial distress prediction specifically within the context of Kenyan SACCOs. The specific objectives included the assessment of the performance of machine learning predictive models using both financial and non-financial variables, the identification of predictors that significantly affect financial distress of Kenyan SACCOs, and determining which features are the most predictive. The study evaluates the effectiveness of various machine learning algorithms, including Decision Tree, K-Nearest Neighbors, Logistic Regression, Artificial Neural Networks, Naive Bayes Classifier, Random Forest, and Support Vector Machine, through nine performance evaluation metrics, with the ROC-AUC score as the primary measure. Results indicate that while K-Nearest Neighbors achieved an ROC-AUC score of 0.78, an ensemble model using Stochastic Gradient Boosting reached 0.81.