Publications:
Lorenzo Lucchese, Mikko S. Pakkanen, Almut E. D. Veraart, The Short-Term Predictability of Returns in Order Book Markets: A Deep Learning Perspective, International Journal of Forecasting, Volume 40, Issue 4, 2024, Pages 1587-1621, ISSN 0169-2070, https://doi.org/10.1016/j.ijforecast.2024.02.001. Code available here.
Lorenzo Lucchese, Mikko S. Pakkanen, Almut E. D. Veraart, Learning with Expected Signatures: Theory and Applications, Forty-second International Conference on Machine Learning, 2025. Code available here.
Lorenzo Lucchese, Mikko S. Pakkanen, Almut E. D. Veraart, Estimation and Inference for Multivariate Continuous-time Autoregressive Processes, Annals of Applied Probability, 2025+ (to appear). Code available here.
PhD Thesis:
Some projects I worked on during the first year of PhD at the Mathematics of Random Systems CDT:
Inconsistent Multi-Modal Models, from ImageSig to MultiSig with Bernat Bassols Cornudella, Joseph Mulligan, Owen Futter, Roan Talbut and William Turner. Industry mini-project in collaboration with DataSig. Code available here.
Solutions of Ordinary Differential Equations as Limits of Pure Jump Markov Processes, A Review (Stochastic Analysis and Partial Differential Equations).
On the Ergodic Rates of Convergence for Markov Processes with Bernat Bassols Cornudella, Joseph Mulligan, and Owen Futter (Advanced Topics in Stochastic Processes).
Multi-Level Monte Carlo Methods for Pricing Collateralized Debt Obligations (Stochastic Methods and Stochastic Algorithms).
Rough Integration, an Introduction with Owen Futter (Advanced Topics in Stochastic Analysis). Presentation.
Vanishing Gradients: from RNNs to LSTMs (Theories of Deep Learning).
MSci Thesis: