Fintech and the digital transformation of financial services have profound implications for market structure and public policy. Our main objective is to use Interpretable Machine Learning (IML) methods to comprehend the rationale behind complex problem-solving approaches and decision making in today’s highly-regulated financial sector. There have been growing calls for making machine learning methods more explainable and for considering the needs of stakeholders, regulators, and end-users of financial products and services. There is a trade-off between performance and interpretability in complex modelling techniques. Black-box models such as neural networks, gradient boosting models or committee-based approaches are becoming standard go-to algorithms given their high performance. However, the internal complexity makes such models hard to understand as no interpretability frameworks are available. On the other hand, less complex models such as linear regression and decision trees may perform poorly but are easier to explain. The area we aim at contributing the most is investment product performance evaluation. We will work towards the development of conceptual and methodological tools for establishing when black-box models are admissible and make them more transparent and explainable. We intend to establish a long-term collaborative relationship with the aim to develop this collaboration post-STSM by applying for larger-scale funding.