Credit-Risk Prediction Model Using Hybrid Deep—Machine-Learning Based Algorithms

Table 7

Performance of hybrid CNN–DT with learning scheme = 80 : 20.

Proposed methods	Criterion	Accuracy	Precision	Recall	F1-score	AUC
CNN–DT (max-depth = 5)	Gini	91.70	97.53	86.95	91.94	91.87
CNN–DT (max-depth = 5)	Entropy	90.70	95.46	86.70	90.87	90.84
CNN–DT (max-depth = 4)	Gini	88.30	91.13	85.66	88.31	88.38
CNN–DT (max-depth = 4)	Entropy	88.20	91.13	85.49	88.22	88.29

Note. n-Estimators = 80, different criterion, and different max-depth.