Accuracy Comparison Between Feedforward Neural Network, Support Vector Machine and Boosting Ensembles for Financial Risk Evaluation

Abstract

Loan defaults have become an increasing concern for lending institutions, presenting significant challenges to profitability and operational stability. However, with the advent of advanced data processing capabilities, greater data availability, and the development of sophisticated machine learning techniques—particularly neural networks—new opportunities have emerged for classifying and predicting loan defaults beyond traditional manual methods. This, in turn, can reduce risk and enhance overall financial performance. In recent years, institutions have increasingly employed these advanced techniques to mitigate the risk of non-performing loans (NPLs) by improving loan approval efficiency. This study aims to address a gap in the literature by examining the predictive performance of different neural network architectures on financial loan datasets. Specifically, it compares the effectiveness of Feedforward Neural Networks (FNNs), Long Short-Term Memory (LSTM) networks, and one-dimensional Convolutional Neural Networks (1D-CNNs) in forecasting loan defaults. Despite the growing body of research in this area, comparative studies focusing on the application of various neural network techniques to loan default prediction remain relatively scarce.