Modern portfolio theory
From log-optimal portfolio theory to risk measures: logarithmic expected shortfall
In this paper, the authors propose a modification of expected shortfall that does not treat all losses equally. We do this in order to represent the worries surrounding big drops that are typical of multiperiod investors.
Machine learning for trading
Gordon Ritter applies reinforcement learning to dynamic trading strategies with market impact
Quant of the year: Jean-Philippe Bouchaud
Risk Awards 2017: Physicist takes on classic models with data and empirical research
The missing piece in operational risk appetite
Setting an op risk appetite is illogical without reference to reward, argues Ariane Chapelle
Stable linear-time optimisation in arbitrage pricing theory models
Gordon Ritter proposes a stable mean-variance optimisation for APT models