China has launched its first artificial intelligence (AI) model designed to analyze the impact of weather patterns on financial markets, marking a new step in climate-sensitive risk management.
According to the China Meteorological Administration (CMA), the Shangji, or "Stock," model was jointly developed by Shanghai-based Fudan University and the China National Meteorological Information Center.
Its core function is to assess how meteorological factors affect asset pricing, offering new tools for investment decisions and financial risk assessment, according to a CMA statement quoted by Science and Technology Daily.
Zhao Yanxia, the model's lead developer and director of the CMA's key open laboratory for financial meteorology, said the model, which utilizes reanalyzed global meteorological data and historical stock trading data, is able to predict short-term returns for most stocks in China's A-share market.
Validation tests show that the model is able to accurately identify industries that are highly sensitive to weather conditions, such as wind and solar power, conventional petrochemicals, construction, and agriculture, thus aligning with international standards.
Zhao explained that the process of evaluating trading strategies using historical data ( backtesting ) for investment strategies based on the model's predictions has shown "sustained and stable positive returns" over various historical periods, demonstrating practical potential.
The model has broad application prospects in the financial sector, said Li Hao, a professor at the Artificial Intelligence Innovation and Incubation Institute at Fudan University and one of the model's creators.
Companies in weather-sensitive industries can use it for climate risk management, while banks and insurance companies can apply it to manage risks in their businesses, such as equity guarantees, and explore climate-related financing, Li said.
The model is useful for investors as a tool in quantitative investing, and academics can use the results to test and refine asset pricing theory, he added.
