Explainability and Stability of Machine Learning Applications — A Financial Risk Management Perspective

With advancement in computing power, hardware, and machine learning algorithms, more and more industry sectors have started to incorporate machine learning in the core business. The adoption of machine learning model in risk management is slower, due to the sensitive nature of the tasks, data involved, and regulatory pressure. This paper evaluates the explainability and stability of machine learning models on a traditional financial risk management task and found out that machine learning models can exhibit an enhanced level of adaptability and stability. However, different models could lead to drastically different performance, which require companies to spend additional resources in training and development. Overall, the net benefits are overwhelming, if done correctly.