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

Figure 4

Architecture of the model: this technique uses four classifiers. The first classifier is a fully connected layer with soft-max that is trained using an end-to-end process, whereas the other three classifiers are binary SVM/RF/DT classifier that is piled on top by removing the final fully connected and soft-max layer. The feature maps that are created by applying a variety of convolutional and pooling layers to the credit data are flattened into a 1D array and utilized as inputs for the support vector machine, random forest, and decision tree.