학술논문
Optimal Systemic Risk Bailout: A PGO Approach Based on Neural Network
Document Type
Working Paper
Author
Source
Subject
Language
Abstract
The bailout strategy is crucial to cushion the massive loss caused by systemic risk in the financial system. There is no closed-form formulation of the optimal bailout problem, making solving it difficult. In this paper, we regard the issue of the optimal bailout (capital injection) as a black-box optimization problem, where the black box is characterized as a fixed-point system that follows the E-N framework for measuring the systemic risk of the financial system. We propose the so-called ``Prediction-Gradient-Optimization'' (PGO) framework to solve it, where the ``Prediction'' means that the objective function without a closed-form is approximated and predicted by a neural network, the ``Gradient'' is calculated based on the former approximation, and the ``Optimization'' procedure is further implemented within a gradient projection algorithm to solve the problem. Comprehensive numerical simulations demonstrate that the proposed approach is promising for systemic risk management.