Order scoring, bandit learning and order cancellations

Xuefeng Gao and Tianrun Xu

Journal of Economic Dynamics and Control, 2022, vol. 134, issue C

Abstract: This paper develops an order scoring model that quantifies the performance of a limit order before execution. Our dynamic stochastic model takes into account of the bid-ask queue imbalance, the queue position of an order and price dynamics. We calibrate and validate the model using the historical order book data and backtesting simulations, and show that our model can perform well empirically. We also combine our model with multi-armed bandit learning to guide order cancellation decisions. We illustrate the empirical performances of various bandit algorithms and show that the Upper Confidence Bound algorithm generally performs the best.

Keywords: Limit order book; Order scoring; Order cancellation; Multi armed bandit (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0165188921002220
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:dyncon:v:134:y:2022:i:c:s0165188921002220

DOI: 10.1016/j.jedc.2021.104287

Access Statistics for this article

Journal of Economic Dynamics and Control is currently edited by J. Bullard, C. Chiarella, H. Dawid, C. H. Hommes, P. Klein and C. Otrok

More articles in Journal of Economic Dynamics and Control from Elsevier
Bibliographic data for series maintained by Catherine Liu ().