1 / 24

Supervised Learning Strategy of Market Making

Supervised Learning Strategy of Market Making. Presented by Ori Gil Supervisor : Gal Zahavi. Winter 2011. Project Overview. Introduce to basic concepts.  Display the main models in the project: Roll model ( 1984 ). Glosten-Milgron model ( 1985 ).

teige
Download Presentation

Supervised Learning Strategy of Market Making

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Supervised Learning Strategy of Market Making Presented by Ori Gil Supervisor : Gal Zahavi Winter 2011 Control and Robotics Laboratory

  2. Project Overview • Introduce to basic concepts.  • Display the main models in the project: • Roll model (1984). • Glosten-Milgron model (1985). • Implement a profitable automated market maker in TASE: • Basic strategy – trading threshold. • Supervised learning strategy – training set and test set. • Simulation on TASE data and conclusions. Control and Robotics Laboratory

  3. Basic Concepts Control and Robotics Laboratory

  4. Leumi’s share (03/01/2010) Price Process Price Process Control and Robotics Laboratory 5

  5. Leumi’s share (03/01/2010) Price Process Control and Robotics Laboratory 5

  6. The Models Population Liquidty Control and Robotics Laboratory

  7. Roll Model (1984) Control and Robotics Laboratory

  8. Roll Model (1984) Control and Robotics Laboratory

  9. GM Model (1985) • Market population Control and Robotics Laboratory

  10. GM Model (1985) • The event tree of a trade: Control and Robotics Laboratory

  11. Analyzing GM Model: Finding The Bid-Ask spread Control and Robotics Laboratory

  12. Market Making Algorithm – Basic approach Estimating μ from Bid(t-1) and Ask(t-1) [GM Model] Cancelling open orders and holding trade work until new order arrives Submitting bid and ask orders : Bid(t)=Bid(t-1) Ask(t)=Ask(t-1) Waiting for new order to arrive at the market μ ? M μ ≤ M μ > M Control and Robotics Laboratory

  13. Market Making Algorithm – Supervised learning approach Gathering training set from TASE quotes D(t)={X(t),Y(t)} Control and Robotics Laboratory

  14. Market Making Algorithm – Supervised learning approach Gathering training set from TASE quotes D(t)={X(t),Y(t)} Gathering training set from TASE quotes D(t)={X(t),Y(t)} Bid price Ask price Informed proportion µ V probability δ Control and Robotics Laboratory

  15. Market Making Algorithm – Supervised learning approach Gathering training set from TASE quotes D(t)={X(t),Y(t)} Running the learned function on the training set (Multi-linear regression) Gathering training set D(t)={X(t),Y(t)} from TASE quotes Control and Robotics Laboratory

  16. Market Making Algorithm – Supervised learning approach Gathering training set from TASE quotes D(t)={X(t),Y(t)} Running the learned function on the training set (Multi-linear regression) Control and Robotics Laboratory

  17. Market Making Algorithm – Supervised learning approach Running our mm strategy on test set and compare results against historical data Gathering training set from TASE quotes D(t)={X(t),Y(t)} Running the learned function on the training set (Multi-linear regression) Producing optimal mm strategy (OLS) Next-step” forecast Control and Robotics Laboratory

  18. Parameters Measure – GM+Roll Control and Robotics Laboratory

  19. Market Making - Basic Strategy “Next-step” Forecast Control and Robotics Laboratory

  20. Supervised Learning Strategy Training Test Control and Robotics Laboratory

  21. Supervised Learning Strategy “Next-step” Forecast Control and Robotics Laboratory

  22. Conclusions • Knowing informed traders population at the market improves our market making performance. • Adding supervised learning solution to the model showed even better performance. • The project has shown success in bringing learning techniques to building market-making algorithms. • Future extensions of this study may include the refinement of the learning techniques. Control and Robotics Laboratory

  23. BIBLIOGRAPHY • Cont R., Stoikov S. and Talreja R., 2010, "A Stochastic Model for Order Book Dynamics, Operations Research, 58, pp. 549–563. • Das, S., 2005. "A Learning Market-Maker in the Glosten-Milgrom Model" Quantitative Finance, 5, 169-180. • Glosten L. R., and P. R. Milgrom, 1985, “Bid, Ask and Transaction Prices in a Specialist Market with Heterogeneously Informed Traders,” Journal of Financial Economics, 14, 71–100. • Huang, R.D. and H. R. Stoll, 1997, “The components of the bid-ask spread: A General approach”, Review of Financial Studies 10, 995-1034. • Roll, R., 1984, “A Simple Implicit Measure of the Effective Bid-Ask Spread in an Efficient Market”, Journal of Finance, 39, 1127–1139. • TASE website, http://www.tase.co.il/TASEEng/Homepage.htm. Control and Robotics Laboratory

  24. Thank You!Questions? Control and Robotics Laboratory

More Related