Market makers facilitate trading in electronic financial markets by simultaneously offering to buy and sell the same asset at any given time. Their role is to provide price stability and increase market liquidity to improve its overall efficiency. Digital assets markets are extremely fragmented and present both challenges and opportunities for market makers. These latter must offer participants accurate prices while balancing their asset inventory on many venues at the same time, what represents a difficult synchronization task.

Predictive modeling of financial data, especially trading activity or asset prices, is a very challenging task. There are a number of novel approaches to feature engineering, data preparation and model architectures that aim to mitigate some of the problems that arise from non-stationarity and other issues typically found in financial time series data.

Optimal trade execution is a well-known problem in quantitative finance. It helps financial actors who trade large quantities of a given asset minimize their risk and their adverse price impact. The problem’s complexity is multiplied when
considering highly fragmented markets, such as those existing today for digital assets. The most recent advances in reinforcement learning and deep learning open the door to a new class of execution algorithms. This data-driven algorithm class reliefs many assumptions from the classical solutions coming from stochastic optimal control theory.