Fraud-related order prediction model training method and device and order prediction method and device

The invention provides a fraud-related order prediction model training method and device and an order prediction method and device. The method comprises the steps of: enabling the training device to extract a list of mobile phone numbers related to fraud from the database in a preset period; acquiring an associated fraud number card order according to the mobile phone number list; extracting feature information of a fraud number card order to generate a negative sample, and extracting feature information of a card number order irrelevant to fraud to generate a positive sample; providing the positive sample and the negative sample to the stacking model, integrating output results of the plurality of sub-models in the first model, and providing the output results to the second model to obtain an output result; determining a loss function value by using the deviation between the output result and the positive sample and the negative sample; and training the stacking model according to the loss function value unt