Entropic Least-Squares Valuation of American Options Subject to Moment Constraints

We propose a new nonparametric method for valuing American options. We extract the risk neutral moments using a set of option data and incorporate them into the entropy framework as constraints to recover the risk-neutral pricing measure. With the recovered risk-neutral measure, we generate paths of the underlying asset returns and determine the optimal exercising strategies via the least-squares algorithm of Longstaff and Schwartz (2001).The results, based on simulations and the IBM option contracts, demonstrate that our method consistently outperforms several alternative methods. Implementation of our method is simple and straightforward