Since the seminar work by Black and Sholes on option pricing early 1970's, many alternative option pricing models have appeared to address some key stylized facts for option markets such as volatility smile, fat-tail, volatility clustering, and so on. Most of the successful option models are parametric models based on di usion processes with jumps usually called the Levy processes and the parameters of the models can be calibrated to t the model to the market option data. Recently nonparametric models have attracted lots of attention to many researchers for their improved prediction accuracy on pricing nancial derivatives mostly for the European options which can be exercised only at its maturities. In the nancial market, however, the most frequently traded options are usually of American type, which can be exercised anytime before their maturities and machine learning models su er from arbitrage opportunities when they are directly applied to pricing real American options. In the present study, we propose a general framework for building a machine learning model that not only satis es no-arbitrage constraints for pricing American options, but also is stable in its prediction to a speci ed range of time-varying daily options. We conduct a comprehensive study to verify the predictive performance of the proposed models by applying them to one-year S&P 100 daily American put options and show that the proposed method is signi cantly better than the state-of arts machine learning models. Also we compare the prediction performance of the machine learning models with parametric jump models when the domain of the in-sample option data is di erent from the domain of the out-of-sample option data and discuss about their limitations.
3. Gencay, R., and Qi, M.: Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging. IEEE Transactions on Neural Networks, 12, 726-734 (2001) 4. Hutchinson, J. M., Lo, A. W., and Poggio, T.: A nonparametric approach to pricing and hedging derivative securities via learning networks. Journal of Finance, 59, 851-889 (1994) 5. Kwon, Y., and Lee, Y.: A second-order tridiagonal method for American option under jump-di usion models. SIAM Journal on Scienti c Computing, 33, 1860-1872 (2011) 6. Park, H., and Lee, J.: Forecasting nonnegative option price distributions using
Bayesian kernel methods. Expert Systems with Applications, 39, 13243-13252 (2012) 7. Yao, J., Li, Y., and Tan, C. L.: Option price forecasting using neural networks.
Omega The International Journal of Management Science, 28, 455-466 (2000)