A Novel Learning Network for Option Pricing with Confidence Interval Information
Nonparametric approaches for option pricing have recently emerged as alternative approaches that complement traditional parametric approaches. In this paper, we propose a novel learning network for option-pricing, which is a nonparametric approach. The main advantages of the proposed method are providing a principled hyper-parameter selection method and the distribution of predicted target value. With these features, we do not need to adjust any parameters at hand for model learning and we can get confidence interval as well as strict predicted target value. Experiments are conducted for the KOSPI200 index daily call options and their results show that the proposed method works excellently to obtain prediction confidence interval and to improve the option-pricing accuracy.
KeywordsMean Square Error Stock Price Gaussian Process Option Price Implied Volatility
Unable to display preview. Download preview PDF.
- 4.Gibbs, M., Mackay, D.J.C.: Efficient Implementation of Gaussian Processes. Draft Manuscript (1992), http://citeseer.nj.nec.com/6641.html
- 7.Lajbcygier, P.: Literature Review: The Problem with Modern Parametric Option Pricing. Journal of Computational Intelligence in Finance 7(5), 6–23 (1999)Google Scholar
- 10.Neal, R.M.: Regression and Classification Using Gaussian Process Priors. Bayesian Statistics 6, 465–501 (1998)Google Scholar
- 11.Rasmussen, C.E.: Evaluation of Gaussian Processes and Other Methods for Non-Linear Regression. PhD Thesis University of Toronto (1996)Google Scholar
- 12.Williams, C.K.I., Rasmussen, C.E.: Gaussian Processes for Regression. NIPS 8, 514–520 (1995)Google Scholar