Answers are grounded in this paper and cite their sources.
This study considered logistic regression and random forest models in modelling the loan default data of German Customers. The data were randomly partitioned into an 80% training set and a 20% test set. The train set was used to fit the data, while the test set served as the out-of-sample data used to evaluate the performance of the model. On the train set, the random forest performs better than the logistic regression model across all the evaluation metrics. On the test dataset, the random forest has superior specificity, precision, accuracy, and F1-score, but the logistic regression model produced a better sensitivity. This means that the model was better at identifying a bad loan; this is, in fact, the desire and priority of every financial institution – a model that is capable of detecting the risk of loan default. In terms of efficiency, the logistic regression model produced lower variance than the random forest, which had high variance.
No takes yet. Share an insight, caveat, or question.
Emmanuel Olamide (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: