|
|
| Title | Modelling the effects of data streams using rough paths theory and its application in finance |
| Time | July 16, 2019 |
| Venue | Valencia, Spain |
| Event | Minisymposia on Machine Learning in Finance - Part 2, International Congress on Industrial and Applied Mathematics (ICIAM) |
| Abstract | Supervised learning problems with sequential input data is an important question due to various applications. One main challenge is the overfitting issue caused the functional type of the input. Motivated by the numerical approximation theory of SDEs, we propose a novel and effective algorithm (Logsig-RNN model) to tackle this problem by combining the rough path theory and RNN. I'll present numerical examples of high frequency financial data to validate the superior performance of our method. |
| URL | Page Link |