Mikko S. Pakkanen

Mikko S. Pakkanen

Reader in Data Science and Quantitative Finance, Imperial College London
Fellow, Data Science Institute


Department of Mathematics
Imperial College London
South Kensington Campus
London SW7 2AZ
United Kingdom

809 Weeks Building (16–18 Prince's Gardens)

+44 20 7594 8541

m.pakkanen@imperial.ac.uk (work)
msp@iki.fi (personal)


I am a Reader in Data Science and Quantitative Finance in the Department of Mathematics at Imperial College London. I have been at Imperial since 2014, except that in 2022–2023 I was an Associate Professor in the Department of Statistics and Actuarial Science at the University of Waterloo, Canada. Earlier in my career I held a postdoctoral fellowship at Aarhus University, Denmark. I received my PhD in Applied Mathematics and MSc in Mathematics from the University of Helsinki, Finland. To see my curriculum vitae, please click here.

My current research is focused on data science, stochastic processes and quantitative finance. My specific interests include:


In the academic year 2023–2024, I teach the following modules at Imperial:


(non-alphabetical order of authors is indicated by an asterisk)


L. Lucchese, M. S. Pakkanen and A. E. D. Veraart
Estimation and inference for multivariate continuous-time autoregressive processes
July 2023, 70 pages.
» e-print: arXiv:2307.13020, code: Github (by L. Lucchese)

P. Murray, R. Passeggeri, A. E. D. Veraart and M. S. Pakkanen*
Feasible inference for stochastic volatility in Brownian semistationary processes
June 2021, 21 pages.
» e-print: arXiv:2007.06357, code: CRAN (by P. Murray)

Articles in refereed journals

L. Lucchese, M. S. Pakkanen and A. E. D. Veraart
The short-term predictability of returns in order book markets: A deep learning perspective
International Journal of Forecasting, to appear.
» article: doi:10.1016/j.ijforecast.2024.02.001, e-print: arXiv:2211.13777, code: Github (by L. Lucchese)

C. Bellani, D. Brigo, M. S. Pakkanen and L. Sánchez-Betancourt
Price impact without averaging
Applied Mathematical Finance 30(4), 175–206, 2023.
» article: doi:10.1080/1350486X.2024.2303078, e-print: arXiv:2110.00771, code: Github (by C. Bellani)

M. S. Pakkanen, X. Miscouridou, M. J. Penn, C. Whittaker, T. Berah, S. Mishra, T. A. Mellan and S. Bhatt*
Unifying incidence and prevalence under a time-varying general branching process
Journal of Mathematical Biology 87, article no. 35, 34 pages, 2023.
» article: doi:10.1007/s00285-023-01958-w, e-print: arXiv:2107.05579, code: GitHub

M. J. Penn, D. J. Laydon, J. Penn, C. Whittaker, C. Morgenstern, O. Ratmann, S. Mishra, M. S. Pakkanen, C. A. Donnelly and S. Bhatt*
Intrinsic randomness in epidemic modelling beyond statistical uncertainty
Communications Physics 6, article no. 146, 9 pages, 2023.
» article: doi:10.1038/s42005-023-01265-2, e-print: arXiv:2210.14221

A. E. Bolko, K. Christensen, M. S. Pakkanen and B. Veliyev
A GMM approach to estimate the roughness of stochastic volatility
Journal of Econometrics 235(2), 745–778, 2023.
» article: doi:10.1016/j.jeconom.2022.06.009, e-print: arXiv:2010.04610

Y. Li, M. S. Pakkanen and A. E. D. Veraart
Limit theorems for the realised semicovariances of multivariate Brownian semistationary processes
Stochastic Processes and their Applications 155, 202–231, 2023.
» article: doi:10.1016/j.spa.2022.10.001, e-print: arXiv:2111.02366

M. Bennedsen, A. Lunde and M. S. Pakkanen
Decoupling the short- and long-term behavior of stochastic volatility
Journal of Financial Econometrics 20(5), 961–1006, 2022.
» article: doi:10.1093/jjfinec/nbaa049, e-print: arXiv:1610.00332

S. Mishra, S. Flaxman, T. Berah, H. Zhu, M. Pakkanen and S. Bhatt*
πVAE: A stochastic process prior for Bayesian deep learning with MCMC
Statistics and Computing 32, article no. 96, 16 pages, 2022.
» article: doi:10.1007/s11222-022-10151-w, e-print: arXiv:2002.06873

M. Morariu-Patrichi and M. S. Pakkanen
State-dependent Hawkes processes and their application to limit order book modelling
Quantitative Finance 22(3), 563–583, 2022.
» article: doi:10.1080/14697688.2021.1983199, e-print: arXiv:1809.08060, code: GitHub (by C. Bellani and M. Morariu-Patrichi)

H. Buehler, P. Murray, M. S. Pakkanen and B. Wood
Deep hedging: Learning to remove the drift
Risk (March 2022), 6 pages.
» article: Risk.net, e-print: arXiv:2111.07844 (extended version)

M. S. Pakkanen, R. Passeggeri, O. Sauri and A. E. D. Veraart
Limit theorems for trawl processes
Electronic Journal of Probability 26, article no. 116, 36 pages, 2021.
» article: doi:10.1214/21-EJP652, e-print: arXiv:2009.10698

C. Heinrich, M. S. Pakkanen and A. E. D. Veraart
Hybrid simulation scheme for volatility modulated moving average fields
Mathematics and Computers in Simulation 166, 224–244, 2019.
» article: doi:10.1016/j.matcom.2019.04.006, e-print: arXiv:1709.01310

M. Bennedsen, U. Hounyo, A. Lunde and M. S. Pakkanen
The local fractional bootstrap
Scandinavian Journal of Statistics 46(1), 329–359, 2019.
» article: doi:10.1111/sjos.12355, e-print: arXiv:1605.00868

M. Morariu-Patrichi and M. S. Pakkanen
Hybrid marked point processes: characterisation, existence and uniqueness
Market Microstructure and Liquidity 4(3&4), 1950007, 55 pages, 2018.
» article: doi:10.1142/S2382626619500072, e-print: arXiv:1707.06970

A. Jacquier, M. S. Pakkanen and H. Stone
Pathwise large deviations for the rough Bergomi model
Journal of Applied Probability 55(4), 1078–1092, 2018.
» article: doi:10.1017/jpr.2018.72, e-print: arXiv:1706.05291
» erratum: doi:10.1017/jpr.2020.109 (with S. Gerhold and T. Wagenhofer)

R. McCrickerd and M. S. Pakkanen
Turbocharging Monte Carlo pricing for the rough Bergomi model
Quantitative Finance 18(11), 1877–1886, 2018.
» article: doi:10.1080/14697688.2018.1459812, e-print: arXiv:1708.02563, code: GitHub (by R. McCrickerd)

M. Bennedsen, A. Lunde and M. S. Pakkanen
Hybrid scheme for Brownian semistationary processes
Finance and Stochastics 21(4), 931–965, 2017.
Reprinted in C. Bayer, P. K. Friz, M. Fukasawa, J. Gatheral, A. Jacquier and M. Rosenbaum (editors): Rough Volatility, pages 127–155, SIAM, Philadelphia, PA, 2023.
» article: doi:10.1007/s00780-017-0335-5, reprint: doi:10.1137/1.9781611977783.ch7, e-print: arXiv:1507.03004

J. Lukkarinen and M. S. Pakkanen
Arbitrage without borrowing or short selling?
Mathematics and Financial Economics 11(3), 263–274, 2017.
» article: doi:10.1007/s11579-016-0180-x, e-print: arXiv:1604.07690

M. S. Pakkanen, T. Sottinen and A. Yazigi
On the conditional small ball property of multivariate Lévy-driven moving average processes
Stochastic Processes and their Applications 127(3), 749–782, 2017.
» article: doi:10.1016/j.spa.2016.06.025, e-print: arXiv:1601.03698

M. S. Pakkanen and A. Réveillac
Functional limit theorems for generalized variations of the fractional Brownian sheet
Bernoulli 22(3), 1671–1708, 2016.
» article: doi:10.3150/15-BEJ707, e-print: arXiv:1404.2822

C. Bender, M. S. Pakkanen and H. Sayit
Sticky continuous processes have consistent price systems
Journal of Applied Probability 52(2), 586–594, 2015.
» article: doi:10.1239/jap/1437658617, e-print: arXiv:1310.7857

O. E. Barndorff-Nielsen, M. S. Pakkanen and J. Schmiegel
Assessing relative volatility/intermittency/energy dissipation
Electronic Journal of Statistics 8(2), 1996–2021, 2014.
» article: doi:10.1214/14-EJS942, e-print: arXiv:1304.6683

M. S. Pakkanen
Limit theorems for power variations of ambit fields driven by white noise
Stochastic Processes and their Applications 124(5), 1942–1973, 2014.
» article: doi:10.1016/j.spa.2014.01.005, e-print: arXiv:1301.2107

E. Bayraktar, M. S. Pakkanen and H. Sayit
On the existence of consistent price systems
Stochastic Analysis and Applications 32(1), 152–162, 2014
» article: doi:10.1080/07362994.2014.858535, e-print: arXiv:0911.3789

J. M. Corcuera, E. Hedevang, M. S. Pakkanen and M. Podolskij
Asymptotic theory for Brownian semi-stationary processes with application to turbulence
Stochastic Processes and their Applications 123(7), 2552–2574, 2013.
» article: doi:10.1016/j.spa.2013.03.011, e-print: arXiv:1211.4221

J. Lukkarinen and M. S. Pakkanen
On the positivity of Riemann-Stieltjes integrals
Bulletin of the Australian Mathematical Society 87(3), 400–405, 2013.
» article: doi:10.1017/S0004972712000639, e-print: arXiv:1203.5276
» erratum: doi:10.1017/S0004972713000713 (included in the arXiv version)

M. S. Pakkanen
Brownian semistationary processes and conditional full support
International Journal of Theoretical and Applied Finance 14(4), 579–586, 2011.
» article: doi:10.1142/S0219024911006747, e-print: arXiv:1002.4774

M. S. Pakkanen
Stochastic integrals and conditional full support
Journal of Applied Probability 47(3), 650–667, 2010.
» article: doi:10.1239/jap/1285335401, e-print: arXiv:0811.1847

M. S. Pakkanen
Microfoundations for diffusion price processes
Mathematics and Financial Economics 3(2), 89–114, 2010.
» article: doi:10.1007/s11579-010-0029-7, e-print: PDF

Articles in refereed conference proceedings

P. Murray, B. Wood, H. Buehler, M. Wiese and M. S. Pakkanen*
Deep hedging: Continuous reinforcement learning for hedging of general portfolios across multiple risk aversions
Proceedings of the 3rd ACM International Conference on AI in Finance (ICAIF’22), New York, NY, USA, October 2022, pages 361–368.
» article: doi:10.1145/3533271.3561731, e-print: arXiv:2207.07467

E. Lappi, M. S. Pakkanen and B. Åkesson
An approximative method of simulating a duel
Proceedings of the 2012 Winter Simulation Conference (WSC’12), Berlin, Germany, December 2012, pages 2330–2339.
» article: doi:10.1109/WSC.2012.6465044

Refereed contributions to edited volumes

B. Horvath, A. Muguruza Gonzalez and M. S. Pakkanen
Harnessing quantitative finance by data-centric methods
In A. Capponi and C.–A. Lehalle (editors): Machine Learning and Data Sciences for Financial Markets: A Guide to Contemporary Practices, pages 265–292, Cambridge University Press, Cambridge, 2023.
» chapter: doi:10.1017/9781009028943.016

Book reviews

M. S. Pakkanen
Review of Quantitative Trading: Algorithms, Analytics, Data, Models, Optimization by X. Guo, T. L. Lai, H. Shek and S. P. Wong
The American Statistician 72(1), 112–113, 2018.
» article: doi:10.1080/00031305.2018.1444855


H. Buehler, P. Murray, M. S. Pakkanen and B. Wood
Deep hedging: Learning risk-neutral implied volatility dynamics
Technical report, July 2021, 18 pages.
» e-print: arXiv:2103.11948

M. Bennedsen, A. Lunde and M. S. Pakkanen
Discretization of Lévy semistationary processes with application to estimation
Technical report, July 2014, 28 pages.
» e-print: arXiv:1407.2754

M. S. Pakkanen
Mathematical aspects of financial markets with frictions
PhD dissertation in Applied Mathematics, under the supervision of Tommi Sottinen and Esa Nummelin.
Department of Mathematics and Statistics, University of Helsinki, October 2010.
» introduction available from: E-thesis

M. Pakkanen
Jatkuvat semimartingaalit ja filtraation alkulaajennus
in Finnish, translated title: "Continuous semimartingales and the initial enlargement of a filtration"
MSc thesis in Mathematics, under the supervision of Tommi Sottinen.
Department of Mathematics and Statistics, University of Helsinki, October 2006.
» full text available from: E-thesis