A Hybrid Deep Learning Approach for Systemic Financial Risk Prediction

Systemic financial risk prediction is a complex nonlinear problem and tied tightly to financial stability since the recent global financial crisis. In this paper, we propose the Systemic Financial Risk Indicator (SFRI) and a hybrid deep learning model based on CNN and BiGRU to predict systemic financial risk. Experiments have been carried out over Chinese economic and financial actual data, and the results demonstrate that the proposed model achieves superior performance in feature learning and outperformance with the baseline methods in both single-step and multi-step systemic financial risk prediction.