Anti-fraud modeling method and anti-fraud monitoring method based on machine learning

Abstract

The invention discloses an anti-fraud modeling modeling method and an anti-fraud monitoring method based on machine learning. The anti-fraud model modeling method based on machine learning comprises the following steps: extracting sample data required for modeling from a database, and carrying out labeling processing on each sample data; matching the association information of each sample data from the database, using the results of labeling processing to establish the multi-dimensional credit data based on the user, and processing and dividing the credit data into training set data and test set data; training and adjusting the parameters of the anti-fraud model by using the training set data; using the test set data to test the anti-fraud model, obtaining the fraud probability value thatthe test set data is fraudulent users. The obtained fraud probability value is compared with the corresponding actual sample situation, and the stability of the anti-fraud model is judged according tothe comparison result, and the anti-fraud statistical threshold value is established. The method can effectively reduce the risk of fraud through label processing and supervised machine learning.

Description

technical field [0001] The invention relates to the field of financial data evaluation, in particular to a machine learning-based anti-fraud model modeling method and an anti-fraud monitoring method. Background technique [0002] The development of Internet technology has created a new round of financial revolution, and it is flourishing under the background of the country's policy of developing inclusive finance. However, excessive growth also contains great blindness, and it is accompanied by increasingly serious financial problems. Credit Risk. In particular, the huge losses caused by the increasingly high-tech and scripted reality of group fraud such as loan fraud and breach of contract, for financial institutions, anti-fraud monitoring for businesses with credit risks has become the key to resisting financial risks. top priority. [0003] At present, it is more common in financial institutions to focus on risk control after lending. In Chinese patent documents, the ti...

AI Technical Summary

Problems solved by technology

Although the invention improves the security and usability of the rule base to avoid the risk of cracking, the number of data samples used is too small to meet the training set data and test set data required by machine learning, thus making it impossible to form a large-scale Judgment threshold based on statistical data; and some steps of the method rely on human experience, and cannot directly give evaluation results and decision-making suggestions for applicant users

Images