Financial risk control method and system integrating deep learning and expert experience

The invention relates to a financial risk control method and system fusing deep learning and expert experience. The method comprises the following steps: performing data exception and missing value detection by using an automation technology; cleaning and correcting the data according to an expert rule base; fusing an automation technology and expert experience to perform feature screening and model selection; performing automatic parameter adjustment on the selected model; and collecting and sorting feedback and suggestions of experts by using an interactive interface. According to the method, by using a mixed feature selection strategy and a model optimization technology, the prediction accuracy and robustness of the model are greatly improved. The invention provides a financial risk control technical scheme integrating automation, accuracy and business interpretation, and the financial risk control method has a great practical value for the financial industry in facing a complex risk environment. 本发明涉及一种融合