PRIVATE DATA PROTECTION-BASED RISK DECISION MAKING METHOD, APPARATUS AND SYSTEM, AND DEVICE

摘要

A private data protection-based risk decision making method, apparatus and system, and a device. Said method is applied to a target member object in target federal learning training, and comprises: inputting a risk feature set belonging to private data into a local first risk control model, and determining a predicted contribution value of a target risk feature dimension, the target risk feature dimension being one of risk feature dimensions corresponding to the risk feature set and the first risk control model, and the first risk control model being obtained by means of target federal learning training; receiving predicted contribution values of the target risk feature dimension sent by other member objects in target federal learning training, a method for determining the predicted contribution values of the target risk feature dimension by the other member objects being consistent with that of the target member object; and on the basis of the predicted contribution values of the target risk feature dimension determined by at least two member objects including the target member object itself, determining interpretation data of the importance of the target risk feature dimension, so as to make a risk decision.