Calibrating rough volatility models: a convolutional neural network approach
About
In this paper we use convolutional neural networks to find the H\"older exponent of simulated sample paths of the rBergomi model, a recently proposed stock price model used in mathematical finance. We contextualise this as a calibration problem, thereby providing a very practical and useful application.
Henry Stone• 2018
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Hurst estimation | fOU (test) | RMSE0.0385 | 20 | |
| Hurst estimation | rHeston (test) | RMSE0.0579 | 20 | |
| Hurst estimation | fBm (test) | RMSE0.105 | 20 | |
| Hurst estimation | Battery capacity proportion series | H-Estimate0.6151 | 7 | |
| Multiple parameters estimation | fOU length 500 (test) | Average RMSE0.489 | 5 | |
| Multiple parameters estimation | rHeston length 500 (test) | Average RMSE0.499 | 5 | |
| Hölder exponent estimation | historic realized volatility data | RMSE0.0697 | 5 |
Showing 7 of 7 rows