Under intermediate volatility and limited samples, model-free DDPG finds dynamic-arbitrage strategies more reliably than SLSQP run on noisily estimated Almgren-Chriss impact parameters, even though the latter knows the true functional form.
Measuring price impact and information content of trades in a time-varying setting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose a non-linear observation-driven version of the Hasbrouck (1991) model for dynamically estimating trades' market impact and information content. We find that market impact displays an intraday pattern superimposed with large fluctuations. Some of them are exogenous, and, as an example, we investigate market impact dynamics around FOMC announcements. Contrary to Hasbrouck (1991), we find that the information content of trades depends on the local liquidity level and the recent history of prices and trades. Finally, we use the model to estimate the time-varying permanent impact parameter, which allows performing a dynamic transaction cost analysis.
fields
q-fin.TR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Reinforcement Learning Efficiently Discover Price Manipulation?
Under intermediate volatility and limited samples, model-free DDPG finds dynamic-arbitrage strategies more reliably than SLSQP run on noisily estimated Almgren-Chriss impact parameters, even though the latter knows the true functional form.