🤖 AI Summary
This study addresses the challenge of identifying whether algorithmic trading strategies act as net consumers or providers of liquidity using only observable transaction and price history, and quantifies their impact on market liquidity and welfare. By integrating multi-period regret decomposition, an AR(1) transaction cost model, and Roll’s implied spread estimator, the authors develop an O(Tnd)-efficient algorithm that, without access to internal signals or objective functions, uniquely recovers the informed trader–market maker dichotomy central to Kyle’s model. The work introduces a liquidity balance condition, uncovers quadratic (N²-scale) fire-sale externalities, and successfully calibrates the framework on CRSP U.S. equity data from 2016 to 2025, effectively capturing liquidity dynamics during the COVID-19 pandemic and the 2022 interest rate shocks.
📝 Abstract
We show that net demand for liquidity by algo strategies is identifiable from its trade and price history alone, with no knowledge of its signal or optimization problem. An exact multi-period regret decomposition implies that the sign of this statistic classifies a linear strategy as a net liquidity consumer or provider, recovering the Kyle (1985) informed-trader/market-maker dichotomy from observables alone. Under an AR(1) cost process, the same statistic equals the product of strategy size and the squared Roll (1984) implied spread, making the correction a direct proxy for prevailing illiquidity. Extending to endogenous price impact and aggregating across N correlated strategies yields a liquidity-balance condition whose violation produces welfare loss scaling as N squared, a closed-form fire-sale externality. We calibrate to CRSP equity data (2016-2025), tracking implied spreads through the COVID-19 and 2022 rate-shock episodes, with an estimator computable in O(Tnd) time.