Abstract: In this talk, we will first review a recent method for solving high-dimensional optimal stopping problems using deep Neural Networks. Second, we propose an alternative algorithm replacing Neural Networks by CART-trees which allow for more interpretation of the estimated stopping rules. We apply our algorithm to multiple examples. We in particular compare the performance of the two algorithms with respect to the Bermudan max-call benchmark example. We also show how our algorithm can be used to plot stopping boundaries.

Unless otherwise specified, in Term 2 and Term 3, the Stochastic Finance seminar takes place on Wednesdays, starting at 11:00 am. In Term 2, the seminar takes place in Room B2.02 (Chemistry and Science Concourse)Link opens in a new window.

While the seminars will run in person, there is also the possibility to join via MS Teams. If you wish to be added to the respective Team, please contact the seminar organiser Miryana GrigorovaLink opens in a new window.

All are welcome.