📝 SummarXiv

Abstract

We consider an irreversible investment problem under incomplete information, where the investor is able to exercise multiple investment rights to a project. The investor does not observe the project value directly and instead only a noisy observation process is observed. Upon each investment, the investor acquires previously hidden information from the project's past (''learning from the past''), and so the learning rate of the problem is controlled by investing. The acquisition of additional information is modeled by letting each investment affect the elapsed time of the observation process. We set up the problem as a recursively defined multiple stopping problem under incomplete information and present the optimal investment strategy as a sequence of stopping boundaries, where the boundaries are solved from equations derived from smooth fit conditions. Examples of optimal boundaries are then solved numerically, and we provide numerical comparative statistics.