ABSTRACT
Market making is a fundamental trading problem in which an agent provides liquidity by continually offering to buy and sell a security. The problem is challenging due to inventory risk, the risk of accumulating an unfavourable position and ultimately losing money. In this paper, we develop a high-fidelity simulation of limit order book markets, and use it to design a market making agent using temporal-difference reinforcement learning. We use a linear combination of tile codings as a value function approximator, and design a custom reward function that controls inventory risk. We demonstrate the effectiveness of our approach by showing that our agent outperforms both simple benchmark strategies and a recent online learning approach from the literature.
- Frederic Abergel, Anirban Chakraborti, Aymen Jedidi, Ioane Muni Toke, and Marouane Anane . 2016. Limit Order Books. Cambridge University Press.Google Scholar
- Jacob Abernethy and Satyen Kale . 2013. Adaptive Market Making via Online Learning. In Proc. of NIPS. 2058--2066. Google ScholarDigital Library
- Marco Avellaneda and Sasha Stoikov . 2008. High-frequency trading in a limit order book. Quantitative Finance, Vol. 8, 3 (2008), 217--224.Google ScholarCross Ref
- Pierre-Luc Bacon, Jean Harb, and Doina Precup . 2016. The Option-Critic Architecture. CoRR Vol. abs/1609.05140 (2016).Google Scholar
- Marc G Bellemare, Will Dabney, and Rémi Munos . 2017. A Distributional Perspective on Reinforcement Learning International Conference on Machine Learning. 449--458.Google Scholar
- Aseem Brahma, Mithun Chakraborty, Sanmay Das, Allen Lavoie, and Malik Magdon-Ismail . 2012. A Bayesian market maker. In Proc. of EC. New York, New York, USA, 215--232. Google ScholarDigital Library
- Álvaro Cartea and Sebastian Jaimungal . 2015. Risk Metrics and Fine Tuning of High-Frequency Trading Strategies. Mathematical Finance, Vol. 25, 3 (2015), 576--611.Google ScholarCross Ref
- Álvaro Cartea, Sebastian Jaimungal, and Damir Kinzebulatov . 2016. Algorithmic Trading with Learning. International Journal of Theoretical and Applied Finance, Vol. 19, 04 (2016), 1650028.Google ScholarCross Ref
- Álvaro Cartea, Sebastian Jaimungal, and José Penalva . 2015. Algorithmic and High-Frequency Trading. Cambridge University Press.Google Scholar
- Álvaro Cartea, Sebastian Jaimungal, and Jason Ricci . 2014. Buy Low Sell High: A High Frequency Trading Perspective. SIAM Journal on Financial Mathematics Vol. 5, 1 (2014), 415--444.Google ScholarDigital Library
- Tanmoy Chakraborty and Michael Kearns . 2011. Market Making and Mean Reversion. In Proc. of EC. 307--314. Google ScholarDigital Library
- Nicholas T. Chan and Christian R. Shelton . 2001. An Electronic Market-Maker. AI Memo 2001-005. MIT AI Lab.Google Scholar
- Hugh L Christensen, Richard E Turner, Simon I Hill, and Simon J Godsill . 2013. Rebuilding the limit order book: sequential Bayesian inference on hidden states. Quantitative Finance, Vol. 13, 11 (2013), 1779--1799.Google ScholarCross Ref
- Dave Cliff . 2006. ZIP60: an enhanced variant of the ZIP trading algorithm CEC/EEE.Google Scholar
- Kristopher De Asis, J Fernando Hernandez-Garcia, G Zacharias Holland, and Richard S Sutton . 2017. Multi-step reinforcement learning: A unifying algorithm. arXiv preprint arXiv:1703.01327 (2017).Google Scholar
- M. A H Dempster and V. Leemans . 2006. An automated FX trading system using adaptive reinforcement learning. Expert Systems with Applications Vol. 30, 3 (2006), 543--552. Google ScholarDigital Library
- Pei-yong Duan and Hui-he Shao . 1999. Multiple Hyperball CMAC Structure for Large Dimension Mapping. Proc. of IFAC, Vol. 32, 2 (1999), 5237--5242.Google ScholarCross Ref
- Dhananjay K. Gode and Shyam Sunder . 1993. Allocative Efficiency of Markets with Zero-Intelligence Traders: Market as a Partial Substitute for Individual Rationality. Journal of Political Economy Vol. 101, 1 (1993), 119--137.Google ScholarCross Ref
- Martin D Gould, Mason A Porter, Stacy Williams, Mark McDonald, Daniel J Fenn, and Sam D. Howison . 2013. Limit order books. Quantitative Finance, Vol. 13, 11 (2013), 1709--1742.Google ScholarCross Ref
- Sanford J Grossman and Merton H Miller . 1988. Liquidity and Market Structure. The Journal of Finance Vol. 43, 3 (1988), 617.Google ScholarCross Ref
- Marek Grzes and Daniel Kudenko . 2010. Reward Shaping and Mixed Resolution Function Approximation. Developments in Intelligent Agent Technologies and Multi-Agent Systems. IGI Global, Chapter 7.Google Scholar
- Olivier Guéant, Charles Albert Lehalle, and Joaquin Fernandez-Tapia . 2013. Dealing with the inventory risk: A solution to the market making problem. Mathematics and Financial Economics Vol. 7, 4 (2013), 477--507.Google ScholarCross Ref
- Fabien Guilbaud and Huyen Pham . 2011. Optimal High Frequency Trading with limit and market orders. CoRR Vol. abs/1106.5040 (2011).Google Scholar
- Seijen Harm van, Hasselt Hado van, Shimon Whiteson, and Marco Wiering . 2009. A theoretical and empirical analysis of expected SARSA Proc. of ADPRL. 177--184.Google Scholar
- Joel Hasbrouck and Gideon Saar . 2013. Low-latency trading. Journal of Financial Markets Vol. 16, 4 (2013), 646--679.Google ScholarCross Ref
- Hado V Hasselt . 2010. Double Q-learning Proc. of NIPS. 2613--2621. Google ScholarDigital Library
- Richard Haynes and John S Roberts . 2015. Automated Trading in Futures Markets. CFTC White Paper (2015).Google Scholar
- Thomas Ho and Hans R. Stoll . 1981. Optimal dealer pricing under transactions and return uncertainty. Journal of Financial Economics Vol. 9, 1 (1981), 47--73.Google ScholarCross Ref
- M. Leaver and T. W. Reader . 2016. Human Factors in Financial Trading: An Analysis of Trading Incidents. Human Factors, Vol. 58, 6 (2016), 814--832.Google ScholarCross Ref
- Hamid Reza Maei, Csaba Szepesvari, Shalabh Bhatnagar, and Richard Sutton . 2010. Toward Off-Policy Learning Control with Function Approximation. Proc. of ICML, 719--726. Google ScholarDigital Library
- Warwick Masson and George Konidaris . 2016. Reinforcement Learning with Parameterized Actions. Proc. of AAAI, 1934--1940. Google ScholarDigital Library
- John E Moody and Matthew Saffell . 1998. Reinforcement Learning for Trading. In Proc. of NIPS. 917--923. Google ScholarDigital Library
- Yuriy Nevmyvaka, Yi Feng, and Michael Kearns . 2006. Reinforcement learning for optimized trade execution Proc. of ICML. 673--680. Google ScholarDigital Library
- Abraham Othman . 2012. Automated Market Making: Theory and Practice. Ph.D. Dissertation. bibinfoschoolCarnegie Mellon University. Google ScholarDigital Library
- Abraham Othman, David M Pennock, Daniel M Reeves, and Tuomas Sandholm . 2013. A Practical Liquidity-Sensitive Automated Market Maker. ACM Transactions on Economics and Computation, Vol. 1, 3 (2013), 1--25. Google ScholarDigital Library
- Rahul Savani . 2012. High-frequency trading: The faster, the better? IEEE Intelligent Systems Vol. 27, 4 (2012), 70--73. Google ScholarDigital Library
- L. Julian Schvartzman and Michael P. Wellman . 2009. Stronger CDA Strategies through Empirical Game-Theoretic Analysis and Reinforcement Learning. Proc. of AAMAS (2009), 249--256. Google ScholarDigital Library
- C R Shelton . 2001. Importance Sampling for Reinforcement Learning with Multiple Objectives. Ph.D. Dissertation. bibinfoschoolMassachusetts Institute of Technology. Google ScholarDigital Library
- Alexander A. Sherstov and Peter Stone . 2004. Three Automated Stock-Trading Agents: A Comparative Study. Agent Mediated Electronic Commerce VI: Theories for and Engineering of Distributed Mechanisms and Systems (AMEC 2004). Vol. Vol. 3435. 173--187. Google ScholarDigital Library
- Tom Spooner, John Fearnley, Rahul Savani, and Andreas Koukorinis . 2018. Market Making via Reinforcement Learning. (2018). showeprint{arxiv}1804.04216 Google ScholarDigital Library
- R.S. Sutton and A.G. Barto . 1998. Reinforcement Learning: An Introduction. IEEE Transactions on Neural Networks Vol. 9, 5 (1998), 1054--1054. Google ScholarDigital Library
- Harm Van Seijen, A Rupam Mahmood, Patrick M Pilarski, Marlos C Machado, and Richard S Sutton . 2016. True online temporal-difference learning. Journal of Machine Learning Research Vol. 17, 145 (2016), 1--40. Google ScholarDigital Library
- Perukrishnen Vytelingum, Dave Cliff, and Nicholas R Jennings . 2008. Strategic bidding in continuous double auctions. Artif. Intell., Vol. 172, 14 (2008), 1700--1729. Google ScholarDigital Library
Index Terms
- Market Making via Reinforcement Learning
Recommendations
Market Making under Order Stacking Framework: A Deep Reinforcement Learning Approach
ICAIF '22: Proceedings of the Third ACM International Conference on AI in FinanceMarket making strategy is one of the most popular high frequency trading strategies, where a market maker continuously quotes on both bid and ask side of the limit order book to profit from capturing bid-ask spread and to provide liquidity to the ...
Deep Reinforcement Learning for Market Making
AAMAS '20: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent SystemsMarket Making is high frequency trading strategy in which an agent provides liquidity simultaneously quoting a bid price and an ask price on an asset. Market Makers reaps profits in the form of the spread between the quoted price placed on the buy and ...
Robust Market Making: To Quote, or not To Quote
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinanceMarket making is a popular trading strategy, which aims to generate profit from the spread between the quotes posted at either side of the market. It has been shown that training market makers (MMs) with adversarial reinforcement learning allows to ...
Comments