Zero-shot adaptation to order book dynamics

TL;DR

This paper introduces an adaptive market-making model that maintains the Avellaneda--Stoikov framework's structure while dynamically adjusting to market regime changes and trading goals.

Contribution

It extends the Avellaneda--Stoikov model by incorporating a measure-style adaptation mechanism that separates market dynamics from trading objectives.

Findings

Maintains fast Hamilton--Jacobi--Bellman structure.

Adapts to changing market regimes.

Converts objectives into optimal quotes via scalarization.

Abstract

We describe an adaptive market-making architecture that preserves the analytical structure of the Avellaneda--Stoikov framework while introducing a successor measure-style adaptation mechanism. In our paper we keep Avellaneda--Stoikov fast Hamilton--Jacobi--Bellman structure and make it adaptive to changing market regimes and trading objectives. The central idea is to separate market dynamics from the trading objective. The market state determines a low-dimensional set of Avellaneda--Stoikov parameters, while recent realized rewards determine a low-dimensional objective vector. The HJB forward map then converts this objective into optimal bid and ask quotes through a scalarization of future reward features.