Sharpe ratio (sometimes also referred to as information ratio) is widely used in asset management to compare and benchmark funds and asset managers. It computes the ratio of the (excess) net return over the strategy standard deviation. However, the elements to compute the Sharpe ratio, namely,...

We present a new methodology of computing incremental contribution for performance ratios for portfolio like Sharpe, Treynor, Calmar or Sterling ratios. Using Euler's ho- mogeneous function theorem, we are able to decompose these performance ratios as a linear combination of individual modi ed...

Can an agent learn efficiently in a noisy and self adapting environment with sequential, non-stationary and non-homogeneous observations? Through trading bots, we illustrate how Deep Reinforcement Learning (DRL) can tackle this challenge. Our contributions are threefold: (i) the use of...

The 2008 financial crisis has severely challenged passive forms of investment. In this paper, we compare two systematic investment processes that a global asset allocator may employ to preserve its capital in the face of a turbulent financial environment. The "risk-driven" allocation, derived...

In 2013, a paper by Google DeepMind kicked off an explosion in Deep Reinforcement Learning (DRL), for games. In this talk, we show that DRL can also be applied to portfolio allocation given various tricks and adaptation specific to non stationary data in finance. We present in particular how to...