Abnormal transaction detection method and device based on transaction rule identification

Abstract

The present invention provides an abnormal transaction detection method and device based on transaction rule identification, wherein the method includes: acquiring transaction detail data of the transaction to be detected, generating a time series to be detected; Quantitative identification model of historical law, obtain the evaluation value of historical law quantitative elements and historical time series corresponding to the transaction to be detected; determine the average amount of information of the time series to be detected according to the time series to be detected and the evaluation value of quantitative elements of historical law; according to the time series to be detected The correlation coefficient value between the sequence and the historical time series, the transaction data variation coefficient value, the average amount of information, the proportion of business units that determine each abnormal situation under the transaction to be detected, and the overall abnormality score of the transaction to be detected. The above technical solution realizes the quantitative identification of various types of abnormal transactions, improves the accuracy and efficiency of abnormal transaction detection, and ensures the reliability and effectiveness of the system.

Description

technical field [0001] The invention relates to the field of abnormal transaction detection, in particular to an abnormal transaction detection method and device based on transaction rule recognition. Background technique [0002] Abnormal transactions refer to transactions with significantly different current operating conditions than in the past. Their occurrence is often related to factors such as risk event outbreaks, market fluctuations, changes in customer groups and business environments, and are the focus of attention in industries such as finance, retail, and logistics. . However, the current detection methods for abnormal transactions still mainly rely on the subjective experience of users (such as managers) and simple transaction data statistics. It is difficult to achieve unified standards, objective science, time-consuming and labor-intensive, and a low level of automation. In addition, there are many types of transactions and different abnormal performances. I...

AI Technical Summary

Problems solved by technology

However, the analysis method based on the comparison of transaction data changes cannot effectively detect the above transaction abnormalities, and does not have the ability to identify complex abnormal situations

In addition, due to the lack of quantitative description capabilities for transaction abnormalities, relying on traditional statistical methods to compare transaction volumes, they can only rely on manual inspections and setting thresholds to identify abnormal transactions. Provide refined decision support information

[0006] For the above problems, no effective solutions have been proposed so far

Images