Matthew Dixon

Matthew Dixon is a British applied mathematician working in the area of algorithmic finance. His research focuses on applying concepts in computational and applied mathematics to financial modeling, especially in the area of algorithmic trading and derivatives. Matthew's research is currently funded by Intel Corporation and he develops codes for high performance architectures. His work in deep learning with Diego Klabjan (NWU) has brought wide recognition and he is a frequently invited speaker at quant and fintech events around the world in addition to be referenced as a computational finance expert in multiple reputed media outlets including the Financial Times and Bloomberg Markets.

Education

Ph.D. Imperial College, London, Applied Mathematics, Mathematics Department
M.Sc. University of Reading, Parallel and Scientific Computation (with distinction)
M.Eng. Imperial College, London, Civil and Environmental Engineering

Research Interests

Fast and scalable computation for financial modeling
Predictive analysis
High-volume data analysis
Financial econometrics; risk management
Derivatives
Machine learning
Quantitative analytics
Algorithmic trading
Monte-Carlo simulations

Awards

2022 Risk Magazine Buy-side Quant of the Year

2021 College of Computing Excellence in Research (Junior level)

Fall 2018 Faculty Innovation Award

Publications

• M. Dixon and J. Goldcamp, Delta-Gamma Component VaR: Non-Linear Risk Decomposition for any Type of Funds, Risk.Net, December 2021.
• M. Dixon and N. Polson, Bayesian Deep Fundamental Factors, contributed chapter to appear in Machine Learning in Financial Markets: A guide to contemporary practices, Eds. Agostino Capponi and Charles-Albert Lehalle, Cambridge University Press, 2021.
• M.F. Dixon and T. Ward, Information-Corrected Estimation: A Generalization Error Reducing Parameter Estimation Method, Entropy, 23(11): 1419, 2021.
• M. Chataigner, A. Cousin, S. Crepey, M.F. Dixon, and D. Gueye, Short Communication: Beyond Surrogate Modeling: Learning the Local Volatility Via Shape Constraints, SIAM Journal of Financial Mathematics, 12(3), pp. SC58-SC69, 2021.
• M. Dixon, Industrial Forecasting with Exponentially Smoothed Recurrent Neural Networks, Technometrics, 64(1), 2021. 
• M. Dixon and I. Halperin, G-Learner and GIRL: Goal Based Wealth Management with Reinforcement Learning, Risk.Net, 2021.
• M. Dixon and J. London, Financial Forecasting with alpha-RNNs: A Time Series Modeling Approach, Front. Appl. Math. Stat., doi: 10.3389/fams.2020.551138, 2020.
• M. Chataigner, S. Crepey, and M. Dixon, Deep Local Volatility, Risks, 8(3), Special Issue on Machine Learning in Finance, Eds. Thorsten Schmidt, Invited Paper, Aug 2020.
• M.F. Dixon, Igor Halperin, and P. Bilokon, Machine Learning in Finance: From Theory to Practice, Textbook, Springer, June 2020.
• M.F. Dixon and N. Polson, Short Communication: Deep Fundamental Factor Models, SIAM Journal of Financial Mathematics, 11(3), featured article, 2020. 
• I. Halperin and M.F. Dixon, "Quantum Equilibrium-Disequilibrium”: Asset Price Dynamics, Symmetry Breaking and Defaults as Dissipative Instantons, Physica A: Statistical Mechanics 537, pp. 122-187, 2020.
• C. Akcora, M.F. Dixon, Y. Gel and M. Kantarcioglu, Blockchain Analytics for Intraday Financial Risk Modeling, Digital Finance, Aug 2019. 
• C. Akcora, M.F. Dixon, Y. Gel and M. Kantarcioglu, Blockchain Data Analytics, IEEE Intelligent Informatics Bulletin, 2019. 
• C. Akcora, M.F. Dixon, Y. Gel, and M. Kantarcioglu. Bitcoin Risk Modeling With Blockchain Graphs, Economic Letters, 2018. 
• M.F. Dixon, N. Polson, and V. Sokolov. Deep Learning for Spatial-Temporal Modeling: Dynamic Traffic Flows and High Frequency Trading. To appear in Applied Stochastic Models in Business and Industry, 2018.
• M.F. Dixon. A High Frequency Trade Execution Model for Supervised Learning. High Frequency, 1(1), pp. 32-52, 2018.
• M.F. Dixon. Sequence Classification of the Limit Order Book using Recurrent Neural Networks. J. Computational Science 24, pp. 277-286, 2017. 
• M.F. Dixon, D. Klabjan, and J. H. Bang. Classification-based Financial Markets Prediction using Deep Neural Networks. Algorithmic Finance 6(3-4), pp. 66-99, 2017. 
• M.F. Dixon, J. Chong and K. Keutzer. Accelerating Value-at-Risk Estimation on Highly Parallel Architectures. Concurrency Computat.: Pract. Exper 24(8), Wiley, pp. 895-907, 2012.

Grants

-Co-PI, NASA AIST Grant, Innovative geometric deep learning models for onboard detection of anomalous events (joint
with Yulia Gel & Baris Coskunuzer, University of Texas, Dallas), June 2022-June 2024.

-PI, Board of Trustees Donor Gift, Forecasting Volatility, May 2022- May 2024.

-Co-PI, NASA JPL R&TD ISC Grant on Topological Data Analysis for
Anomaly Detection in Multi-Resolution Satellite Observations of Aerosols (joint
with Yulia Gel, University of Texas, Dallas), June 2021.

-PI, Dell Technologies Gift, HPC, AI and Algorithmic Trading, Jan - May 2021.

-Co-PI, NSF ERC Planning Grant, FinTech for Infrastructure (joint with
Peter Adrieans, University of Michigan), Award #:1840433. Aug. 2018 - Aug.
2019.

-PI, Intel Corp. Gift, High Performance Computational Finance, Aug. 2016- June 2019.

Affiliations

Master of Financial Technology

M.S. in Finance

Expertise

Computational finance, statistical machine learning, scientific computing, fintech