As the global economy gradually enters the post-pandemic era, the prediction of financial distress in listed companies is of significant importance to investors and regulatory authorities. This study employs financial data from Chinese listed companies, integrating macroeconomic factors and industry policy information, and applies neural network and LassoNet regression to construct predictive models. By analyzing data from a-share listed companies from 2000 to 2018, this research considers multi-dimensional factors including financial ratios, corporate governance, macroeconomics, and industry policies, aiming to enhance the accuracy of corporate financial distress prediction. The expected results suggest that the neural network model incorporating macroeconomic factors and industry policies can effectivelyidentify the significant factors influencing financial distress and improve the performance of financial distress prediction.