Credit card abnormal transaction behavior judgment method and system based on deep learning

The invention discloses a credit card abnormal transaction behavior determination method and system based on deep learning, and belongs to the technical field of big data application. The method comprises the steps: inputting credit card transaction data into a pre-trained deep neural network model, and the deep neural network model comprises a feature extraction network and a transaction behaviordetermination network; processing the credit card transaction data by using a feature extraction network to obtain a time sequence feature vector group corresponding to the credit card transaction data; and processing the time sequence feature vector group by using a transaction behavior judgment network to obtain a fraud classification result corresponding to the credit card transaction data. The constructed deep learning anti-fraud model can effectively distinguish the abnormal transaction behaviors of the credit card, and further improves the discrimination accuracy of the transaction fraud behaviors of the credit