Applications of Machine Learning to Estimating the Sizes and Market Impact of Hidden Orders in the BRICS Financial Markets

  • Witness MAAKE University of the Witwatersrand, South Africa
  • Terence VAN ZYL Institute for Intelligent Systems University of Johannesburg, South Africa


The research aims to investigate the role of hidden orders on the structure of the average market impact curves in the five BRICS financial markets. The concept of market impact is central to the implementation of cost-effective trading strategies during financial order executions. The literature is replicated using the data of visible orders from the five BRICS financial markets. We repeat the implementation of the literature to investigate the effect of hidden orders. We subsequently study the dynamics of hidden orders. The research applies machine learning to estimate the sizes of hidden orders. We revisit the methodology of the literature to compare the average market impact curves in which true hidden orders are added to visible orders to the average market impact curves in which hidden orders sizes are estimated via machine learning.

The study discovers that: (1) hidden orders sizes could be uncovered via machine learning techniques such as Generalized Linear Models (GLM), Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Random Forests (RF); and (2) there exist no set of market features that are consistently predictive of the sizes of hidden orders across different stocks. Artificial Neural Networks produce large R2 and small Mean Squared Error on the prediction of hidden orders of individual stocks across the five studied markets. Random Forests produce the most appropriate average price impact curves of visible and estimated hidden orders that are closest to the average market impact curves of visible and true hidden orders. In some markets, hidden orders produce a convex power-law far-right tail in contrast to visible orders which produce a concave power-law far-right tail. Hidden orders may affect the average price impact curves for orders of size less than the average order size; meanwhile, hidden orders may not affect the structure of the average price impact curves in other markets. The research implies ANN and RF as the recommended tools to uncover hidden orders.


[1] Alfonsi, A., Schied, A., Slynko, A., 2009. Order book resilience, price manipulation, and positive portfolio problem. SIAM Journal on Financial Mathematics, Forthcoming, 24 p. Available at: abs/10.1137/090762786
[2] Alfonsi, A., Schied, A. 2010. Optimal trade execution and absence of price manipulations in limit order book models. SIAM Journal on Financial Mathematics, 1(1): 490–522. Available at: 10.1137/090762786
[3] Bouchaud, J.P. 2017. Price impact, capital fund management, encyclopedia of quantitative finance, John Wiley Sons Ltd. Available at:
[4] Breiman, L. 2001. Random forests. Machine Learning, 45: 5–30. Available at: doi/abs/10.1177/1536867X20909688?journalCode=stja
[5] Easely, D., Keifer, N.M., O’Hara, M. 2002. Is information risk a determinant of asset returns? Journal of Finance, 57(5): 2185-2221. Available at:
[6] Fan, R.E., Chen P.H., Lin C.J. 2005. Working set selection using second order information for training support vector machines. The Journal of Machine Learning Research, 6: 1871–1918. Available at: doi/10.5555/2627435.2627437
[7] Farmer, J.D., Lillo, F. 2004. On the origin of power-law tails in price fluctuations. Quantitative Finance, 4: 7–11. Available at:
[8] Gatheral, J. 2010. No-dynamic-arbitrage and market impact. Quantitative Finance, 10(7): 749-759. Available at:
[9] Gatheral, J., Schied, A., Slynko, A. 2010. Transient linear price impact and Fredholm integral equations. Mathematical Finance, Forthcoming, 30 p. Available at: 228231758_Transient_Linear_Price_Impact_and_ Fredholm_Integral_Equations
[10] Glosten, L.R., Milgrom, P.R. 1985. Bid, ask and transaction prices in a specialist market with heterogeneously informed traders. Journal of Financial Economics, 14(1): 71–100. Available at:
[11] Hagan, M.T., Menhaj, M. 1994. Training feed forward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6): 989–993. Available at:
[12] Harvey, M., Hendricks, D., Gebbie, T., Wilcox, D. 2017. Deviations in expected price impact for small transaction volumes under fee restructuring, Elsevier B.V. Physica A, 471(1): 416-426. Available at:
[13] Lillo, F., Mantegna, R., Farmer, J.D. 2003. Master curve for price-impact function. Nature, 421 (6919): 129-130. Available at:
[14] Marquardt, D. 1963. An algorithm for least-squares estimation of nonlinear parameters, SIAM Journal on Applied Mathematics, 11(2): 431–441. Available at:
[15] Nguyen, D., Widrow, B. 1990. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. IJCNN International Joint Conference on Neural Networks, 21–26 pp. Available at:
[16] O’Hara, M. 1998. Market Microstructure Theory. Blackwell, Oxford. ISBN-10: 0631207619, ISBN-13: 978-0631207610, 300 p.
[17] Potters, M., Bouchaud, J.P. 2003. More statistical properties of order books and price impact. Physica, A: Statistical Mechanics and its Applications, 324 (1–2): 133-140. Available at: science/article/abs/pii/S0378437102018964
[18] Seber, G.A.F. 1977. Linear regression analysis. New York: Wiley. 2nd Edition. ISBN: 0471019674, 9780471019671, 465 p. Available at: Error! Hyperlink reference not valid.
[19] Vapnik, V. 1995. The nature of statistical learning theory. Springer, New York. ISBN: 0-387-98780-0. Available at:
How to Cite
MAAKE, Witness; VAN ZYL, Terence. Applications of Machine Learning to Estimating the Sizes and Market Impact of Hidden Orders in the BRICS Financial Markets. Journal of Advanced Studies in Finance, [S.l.], v. 11, n. 1, p. 28-64, aug. 2020. ISSN 2068-8393. Available at: <>. Date accessed: 17 may 2022. doi:
Journal of Advanced Studies in Finance