The main goal of this paper is to introduce a new financial stress indicator, signaling regime transitions from stability to turbulence. This indicator is based on the combination of a wide range of market prices of risk, properly normalized to make them comparable across markets and time...

We consider a gradient boosting decision trees (GBDT) approach to predict large S&P 500 price drops from a set of 150 technical, fundamental and macroeconomic features. We report an improved accuracy of GBDT over other machine learning (ML) methods on the S&P 500 futures prices. We show that...

Deep reinforcement learning (DRL) has reached super human levels in complex tasks like game solving (Go, StarCraft II, Atari Games), and autonomous driving. However, it remains an open question whether DRL can reach human level in applications to financial problems and in particular in detecting...

There is an important information deficit on political and financial risks in Africa. This paper fills this gap by compiling a unique database of financial (sovereign, banking, currency, expropriation) and political crises (regime changes, ethnic and revolutionary wars, genocides, armed...