Avellaneda-Stoikov 和 Cartea-Jaimungal 作为统一框架:库存做市的强制唯一性定理
Avellaneda-Stoikov and Cartea-Jaimungal as One Framework: A Forced Uniqueness Theorem for Inventory Market Making
AI总结:
本文通过公理推导证明,库存做市中的两个经典框架(Avellaneda-Stoikov 和 Cartea-Jaimungal)并非独立,而是同一偏好泛函的不同表现,并给出了参数间的强制关系。
摘要:
在库存做市中,Cartea-Jaimungal 框架的运行惩罚系数 $\phi$ 和 Avellaneda-Stoikov 框架的风险厌恶参数 $\gamma$ 通常被视为独立的自由参数,分别进行校准。我们证明它们实际上并非独立。对做市商动态偏好泛函的一组小公理,即现金可加性、归一化、凹性、强动态一致性和律不变性,强制偏好泛函为清算调整后终端财富的熵确定性等价,由单个正标量 $\gamma$ 参数化。Avellaneda-Stoikov 框架是该公理类的唯一代表。Cartea-Jaimungal 框架是其关于库存量大小的二阶泰勒展开,运行系数强制为 $\phi = \gamma \sigma^2/2$,且在清算成本的温和正则条件下,终端系数强制为 $\alpha = \frac{1}{2} L''(0)$。这两个通常被视为竞争性替代方案、选择由可处理性驱动的框架,是同一底层对象的不同表现形式。强制关系是可逆的,$\gamma = 2\phi/\sigma^2$,为独立校准的交易台参数提供了一致性交叉检验。
英文摘要:
In inventory market making, the running-penalty coefficient $ϕ$ of the Cartea-Jaimungal framework and the risk-aversion parameter $γ$ of the Avellaneda-Stoikov framework are typically treated as independent free parameters, calibrated separately. We show that they are in fact not independent. A small set of axioms on the market maker's dynamic preference functional, namely cash-additivity, normalization, concavity, strong dynamic consistency, and law-invariance, forces the preference functional to be the entropic certainty-equivalent on liquidation-adjusted terminal wealth, parametrized by a single positive scalar $γ$. The Avellaneda-Stoikov framework is the unique representative of this axiom class. The Cartea-Jaimungal framework is its second-order Taylor expansion in inventory magnitude, with the running coefficient forced to $ϕ= γσ^2/2$ and (under a mild regularity condition on the liquidation cost) the terminal coefficient forced to $α= \frac{1}{2}L''(0)$. The two frameworks, typically presented as competing alternatives with the choice between them driven by tractability, are different manifestations of a single underlying object. The forced relation is invertible, $γ= 2ϕ/σ^2$, giving a consistency cross-check on independently calibrated desk parameters.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。