Responsible Credit Risk Assessment with Machine Learning and Knowledge Acquisition

Abstract

Making responsible lending decisions involves many factors. There is a growing amount of research on machine learning applied to credit risk evaluation. This promises to enhance diversity in lending without impacting the quality of the credit available by using data on previous lending decisions and their outcomes. However, often the most accurate machine learning methods predict in ways that are not transparent to human domain experts. A consequence is increasing regulation in jurisdictions across the world requiring automated decisions to be explainable. Before the emergence of data-driven technologies lending decisions were based on human expertise, so explainable lending decisions can, in principle, be assessed by human domain experts to ensure they are fair and ethical. In this study we hypothesised that human expertise may be used to overcome the limitations of inadequate data. Using benchmark data, we investigated using machine learning on a small training set and then correcting errors in the training data with human expertise applied through Ripple-Down Rules. We found that the resulting combined model not only performed equivalently to a model learned from a large set of training data, but that the human expert’s rules also improved the decision making of the latter model. The approach is general, and can be used not only to improve the appropriateness of lending decisions, but also potentially to improve responsible decision making in any domain where machine learning training data is limited in quantity or quality.

Data analysis with different variables and credit risk assessment

“…Paweł Pławiak et al .applied a novel approach based on deep genetic cascade ensemble of different support vector machine (SVM) classifiers (called Deep Genetic Cascade Ensembles of Classifiers (DGCEC)) to the Statlog Australian data [5]. Charles Guan et al .combined ML classification models trained on limited data with a well established form of " human-in-the-loop" knowledge acquisition based on Ripple-Down Rules (RDR) to construct fair and compliant rules that could also improve overall performance [6]. David West investigates the credit scoring accuracy of five neural network models: multilayer perceptron, mixture-of-experts, radial basis function, learning vector quantization, and fuzzy adaptive resonance.…”

Application of AdaBound-Optimized XGBoost-LSTM Model for Consumer Credit Assessment in Banking Industries

“…First, with the continuous changes in the financial market and the continuous innovation of financial products, traditional credit assessment models may not perform well in dealing with complex and changeable financial environments (Luo & Zhang, 2022). Second, traditional credit assessment mainly relies on static historical data and rules, which makes it difficult to capture the dynamic changes in personal credit risk (Guan et al, 2023). Third, in the context of huge amounts of data, traditional methods may be inefficient when processing large-scale data, and it is difficult to handle nonlinear and high-dimensional features.…”