Deep Generators on Commodity Markets Application to Deep Hedging

Four deep generative methods for time series are studied on commodity markets and compared with classical probabilistic models. The lack of data in the case hedgers is a common flaw, which seek to address. In specific commodities, it turns out that these generators can also be used refine price models by tackling high-dimensional challenges. this work, synthetic prices produced such then train various options. A fully data-driven approach risk management thus proposed, from generation learning hedging policies.