Method and device for identifying fraud and electronic equipment

Abstract

The invention provides a method and device for identifying fraud and electronic equipment, and the method comprises the steps: identifying to-be-identified behavior data based on a classification model; when the to-be-identified behavior data is abnormal, determining an auditing result of the to-be-identified behavior data; taking the to-be-identified behavior data as a positive sample and addingthe positive sample into a preset sample set; taking the to-be-identified behavior data as historical behavior data, and extracting outlier historical behavior data corresponding to outliers in the historical behavior data based on a preset outlier detection model; and when the outlier historical behavior data belongs to fraudulent behaviors, adding the outlier historical behavior data as a positive sample into the sample set, and then training the classification model again based on the updated sample set. Through the technical scheme provided by the embodiment of the invention, the number ofsamples in the sample set is increased, the classification model can identify novel fraud behaviors in time, and the identification effect of the classification model is improved.

Description

technical field [0001] The present invention relates to the technical field of behavior recognition, in particular to a fraud recognition method, device, electronic equipment and computer-readable storage medium. Background technique [0002] At present, fraud and other illegal activities exist in many industries, such as telecommunication fraud, medical insurance fraud, and commercial insurance fraud. At present, manual review is mainly used to identify illegal activities, but the cost of manual review is high and the efficiency is low; if the efficiency is improved, it will be prone to errors. [0003] With the development of artificial intelligence fields such as machine learning, people have begun to try to apply machine learning to fraud detection scenarios. However, in various industries, fraudulent behaviors are in the minority, that is, most of the data are negative samples of non-fraudulent behaviors, while the number of positive samples belonging to fraudulent beh...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem of low accuracy in the identification of existing fraudulent behaviors, the embodiments of the present invention provide a method, device, electronic equipment, and computer-readable storage medium for identifying fraudulent behaviors.

Images