Dieter Hendricks

Senior Project Research Fellow


Dieter's research lies in the domain of computational and mathematical finance. Key interests include understanding high frequency market microstructure, dimensionality reduction and optimal control in complex adaptive systems. His PhD work developed techniques for online learning in high-frequency financial markets, focusing on scale-specific state representation and constrained interaction under a reinforcement learning paradigm.


Dieter's current role involves working with the BNP Paribas Capital Markets quantitative research team, where they are investigating the use of probabilistic generative models for client recommendations to assist sales traders. Another project considers the nature of adverse selection in OTC markets and how this may be accounted for in market making. Within the Machine Learning Research Group, Dieter is working on projects which explore the nuances of applying state-of-the-art machine learning techniques to market microstructure problems. A key focus is on dimensionality reduction for limit order books and data-driven approaches to eliciting effective reward functions/agent objectives at different hierarchies or scales of intraday microstructure.


Related Events

10th Anniversary Oxford-Man Institute Annual Workshop

Working Paper

Hendricks, D. and Wilcox, D (2014). A reinforcement learning extension to the Almgren-Chriss framework for optimal trade execution. IEEE CIFEr.
Hendricks, D (2016). Using real-time cluster configurations of streaming asynchronous features as online state descriptors in financial markets.
Hendricks, D. and Roberts, S.J. (2017). Optimal client recommendation for market makers in illiquid financial products.

Published Research

Harvey, M., Hendricks, D., Gebbie, T. and Wilcox, D (2017). Deviations in expected price impact for small transaction volume under fee restructuring. Physica A. 471. 416-426.
Hendricks, D., Gebbie,, T. and Wilcox, D (2016). Detecting intraday financial market states using temporal clustering. Quantitative Finance. 16(11). 1657-1678.
Hendricks, D., Gebbie, T. and Wilcox, D (2016). High-speed detection of emergent market clustering via an unsupervised parallel genetic algorithm. South African Journal of Science. 112(1/2). 9.
Franke, B., Plante, J.F., Roscher, R., Lee, A., Smyth, C., Hatefi, A., Chen, F., Gil, E., Schwing, A. and Hendricks, D (2016). Statistical inference, learning and models in big data. International Statistical Review. 84(3). 371-389.