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.