Deep Learning of Robust Market Making under Regime-Switching Order Flow

By Felipe Moret, Fabrizio Lillo

Published 2026-09-10

Everscope rating

1854

Relevance to quantitative trading

10 / 10

Implementation complexity

8 / 10

Reproducibility

5 / 5

About this paper

Methodology: Rainbow Distributional DQN with Bayesian Regime Belief and Scenario-Bandit Fine-Tuning. Problem types: Reinforcement Learning, Market Making, Optimization, Online Learning, Risk Management.

arXiv:2609.11614 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.