Chebyshev Tensors and Machine Learning in DIM Calculations - Slides
In this presentation we see how Chebyhsev Tensors and Machine Learning techniques can be used in the calculation of Dynamic Initial Margin (DIM).
We start by giving an overview of the main mathematical properties behind Chebyhsev Tensors. Then we see how these can be used to approximate pricing functions within risk calculations to alleviate the huge computational burden associated with them.
Finally we explain how Chebyshev Tensors can be used in the calculation of DIM and present DIM calculations obtained Chebyshev Tensors, Deep Neural Networks and other regression types.
-
Pricing problem in risk calculations
-
DIM, its challenges and different ways to compute it: Machine Learning, Chebyshev Tensors
-
Chebyshev mathematical framework
-
How to use Chebyshev Tensors in risk calculations
-
Chebyshev Tensors applied to DIM
-
DIM results using Chebyshev Tensors, regressions and Deep Neural Nets
Presenter: Mariano Zeron: Head of Research and Development: MoCaX Intelligence
Mariano leads our Research & Development work. He has vast experience in Chebyshev Spectral Decomposition, machine-learning and related disciplines, and their application to quantitative problems in the financial markets. Mariano holds a Ph.D. in Mathematics from Cambridge University.
