On Optimal Dividend and Investment Strategy under Renewal Risk Models

TL;DR

This paper advances the understanding of optimal dividend and investment strategies under renewal risk models by constructing epsilon-optimal policies and analyzing the associated complex PDEs and stochastic systems.

Contribution

It develops a method to construct epsilon-optimal strategies under renewal risk models and addresses the regularity and well-posedness challenges of related PDEs and stochastic systems.

Findings

Constructed epsilon-optimal strategies for renewal risk models.

Proved well-posedness of the closed-loop stochastic system.

Analyzed the regularity of viscosity solutions to complex PDEs.

Abstract

In this paper we continue investigating the optimal dividend and investment problems under the Sparre Andersen model. More precisely, we assume that the claim frequency is a renewal process instead of a standard compound Poisson process, whence semi-Markovian. Building on our previous work \cite{BaiMa17}, where we established the dynamic programming principle via a {\it backward Markovization} procedure and proved that the value function is the unique {\it constrained} viscosity solution of the HJB equation, in this paper we focus on the construction of the optimal strategy. The main difficulties in this effort is two fold: the regularity of the viscosity solution to a non-local, nonlinear, and degenerate parabolic PDE on an unbounded domain, which seems to be new in its own right; and the well-posedness of the closed-loop stochastic system. By introducing an auxiliary PDE, we construct an $\e$-optimal strategy, and prove the well-posedness of the corresponding closed-loop system, via a "bootstrap" technique with the help of a Krylov estimate.