|
on Market Microstructure |
| By: | Xue-Zhong He (Finance Discipline Group, UTS Business School, University of Technology Sydney); Shen Lin |
| Abstract: | Information-based reinforcement learning is effective for trading and price discovery in limit order markets. It helps traders to learn a statistical equilibrium in which traders' expected payoffs and out-sample payoffs are highly correlated. Consistent with rational equilibrium models, the order choice between buy and sell and between market and limit orders for informed traders mainly depends on their information about fundamental value, while uninformed traders trade on a short-run momentum of the informed market orders. The learning increases liquidity supply of uninformed and liquidity consumption of informed, generating diagonal effect on order submission and hump-shaped order books, and improving traders' profitability and price discovery. The results shed a light into the market practice of using machine learning in limit order markets. |
| Keywords: | Reinforcement Learning; Order Book Information; Limit Orders; Momentum Trading |
| JEL: | G14 C63 D82 D83 |
| Date: | 2019–02–01 |
| URL: | http://d.repec.org/n?u=RePEc:uts:rpaper:403&r=all |
| By: | F. Douglas Foster; Xue-Zhong He (Finance Discipline Group, UTS Business School, University of Technology Sydney); Junqing Kang; Shen Lin |
| Abstract: | We propose a nonlinear rational expectations equilibrium model of high-frequency endogenous liquidity provision to explore fragile liquidity. With fast trading speed and private information, high-frequency traders can either compete with designated market makers (DMMs) by providing liquidity or attempt to profit from speculative trades that consume liquidity. The risk from this endogenous liquidity provision, coupled with limits to participation by DMMs, intensifies the adverse selection faced by DMMs. This can generate a gap between liquidity supply from DMMs and liquidity demand by informed traders. As a result, endogenous liquidity provision produces fragile liquidity, with the possibility of market breaks when high-frequency traders switch from liquidity provision to liquidity consumption on the basis of unexpected information signals. |
| Keywords: | endogenous liquidity provision; fragile liquidity; machine learning |
| JEL: | G10 G14 |
| Date: | 2019–11–01 |
| URL: | http://d.repec.org/n?u=RePEc:uts:rpaper:402&r=all |
| By: | Marco Cipriani; Roberta De Filippis; Antonio Guarino; Ryan Kendall |
| Abstract: | We examine how professional traders behave in two financial market experiments; we contrast professional traders’ behavior to that of undergraduate students, the typical experimental subject pool. In our first experiment, both sets of participants trade an asset over multiple periods after receiving private information about its value. Second, participants play the Guessing Game. Finally, they play a novel, individual-level version of the Guessing Game and we collect data on their cognitive abilities, risk preferences, and confidence levels. We find three differences between traders and students: Traders do not generate the price bubbles observed in previous studies with student subjects; traders aggregate private information better; and traders show higher levels of strategic sophistication in the Guessing Game. Rather than reflecting differences in cognitive abilities or other individual characteristics, these results point to the impact of traders’ on-the-job learning and traders’ beliefs about their peers’ strategic sophistication. |
| Keywords: | bubbles; experiments; financial markets; information aggregation; professional traders; strategic sophistication |
| JEL: | C93 G11 G14 |
| Date: | 2020–08–01 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fednsr:88552&r=all |