Research projects

Project CEMAPRE internal

TitleExplainable machine learning models in financial economics
ParticipantsJoão Bastos (Principal Investigator)
SummaryMachine learning based predictive techniques are increasingly being adopted in finance and
economics. However, due to their complexity and high number of degrees of freedom, their predictions
are often difficult to explain and validate. This is referred to as the “black box” problem. In
financial economics, we often want to know which factors drove a particular decision, which would
preclude the use of opaque models. In this project, we will investigate several approaches for
"x-raying" black-box models, and their viability to address problems in financial economics.