Learning short-option valuation in the presence of rare events
We present a neural-network valuation of financial derivatives in the case of fat-tailed underlying asset returns. A two-layer perceptron is trained on simulated prices taking into account the well-known effect of volatility smile. The prices of the underlier are generated using fractional calculus algorithms, and option prices are computed by means of the Bouchaud-Potters formula. This learning scheme is tested on market data; the results show a very good agreement between perceptron option prices and real market ones.
Year of publication: |
2000-01
|
---|---|
Authors: | Raberto, M. ; Cuniberti, G. ; Scalas, E. ; Riani, M. ; Mainardi, F. ; Servizi, G. |
Institutions: | arXiv.org |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Waiting-times and returns in high-frequency financial data: an empirical study
Raberto, M., (2002)
-
Asset-asset interactions and clustering in financial markets
Cuniberti, G., (2001)
-
Liquid markets and market liquids: collective and single-asset dynamics in financial markets
Cuniberti, G., (2001)
- More ...