Valentin Tissot-Daguette

Title: Neural Optimal Stopping Boundary

Abstract: A method based on neural networks is developed to calculate the boundary separating the stopping and continuation regions in optimal stopping. The algorithm parameterizes the boundary as the graph of a function and introduces relaxed stopping rules using fuzzy boundaries to facilitate efficient optimization. Several financial instruments are analyzed through this method, demonstrating its effectiveness. The existence of the stopping boundary is also proved under natural structural assumptions.