Abstract: The reasons for credit spreads can be divided into enterprise-specific non-systematic risks and widespread macroeconomic systemic risks. The previous traditional research mainly focused on the perspective of unsystematic risk. However, at present, more and more scholars are beginning to focus on systemic risks. Based on the neural network algorithm, this paper constructs an improved neural network-based corporate bond spread model to explore the impact of macro systemic risks on credit spreads. Based on the multi-factor no-arbitrage model, the linear relationship between the credit spread and the risk premium of each factor is obtained. At the same time, based on previous research results and observations of the current market reality, this paper identifies five important macroeconomic factors: actual economic output factors, inflation factors, stock market volatility factors, stock market return factors and inter-bank funding factors. The research results show that the model constructed in this paper has excellent performance.
Keywords: Neural network, improved algorithm, corporate bond spread model, model simulation
