FINTECH THRUST SEMINAR | Gaussian Process Models for Quantitative Finance
Supporting the below United Nations Sustainable Development Goals:支持以下聯合國可持續發展目標：支持以下联合国可持续发展目标：
Gaussian Process Models for Quantitative Finance
Abstract:
I will present an overview and a brief tutorial on Gaussian Process (GP) models which offer a flexible probabilistic framework for functional approximation and interpolation. The first half will survey GP training, kernel selection, and observation noise modeling. The second half will highlight two applications of GPs in quantitative finance: (i) statistical learning and uncertainty quantification of derivative contract sensitivities using GP gradients; (ii) probabilistic curve-fitting for commodity forward curves, offering a new perspective on seasonality and factor decomposition.
Mike Ludkovski is a Professor of Statistics and Applied Probability at University of California Santa Barbara where he co-directs the Center for Financial Mathematics and Actuarial Research. Among his research interests are Monte Carlo techniques for optimal stopping/stochastic control, modeling of renewable energy markets, Gaussian process models for quantitative finance, and non-zero-sum stochastic games. His research has been supported by NSF, DOE, ARPA-E and CAS. He holds a Ph.D. in Operations Research and Financial Engineering from Princeton University and has held visiting positions at London School of Economics and Paris Dauphine University.