Click farming detecting method based on user behavior data characteristic and system thereof

Abstract

The invention provides a click farming detecting method based on a user behavior data characteristic and a system thereof. The method comprises the steps of acquiring transaction behavior informationof a current to-be-detected transaction, wherein the transaction behavior information comprises a multidimensional behavior characteristic attribute; inputting the traction behavior information into apre-established big data outlier prediction model, extracting the behavior characteristic attribute of the outlier in the current to-be-detected transaction, and determining a fact that a corresponding traction behavior is an abnormal transaction behavior; for aiming at behavior characteristic attribute of each outlier of the abnormal transaction behavior, acquiring a decision tree which is constructed based on the behavior characteristic attribute that corresponds with the outlier, thereby determining whether the abnormal transaction behavior is a click farming behavior. The click farming detecting method effectively prevents defects such as relatively low identification rate and easy failure in coping with more and more professional click farming tools by existing click farming preventing modes based on order sales statistics or simple rules.

Description

technical field [0001] The invention relates to the field of e-commerce information technology, in particular to a method and system for detecting swiping orders based on user behavior data characteristics. Background technique [0002] Today, with the rapid development of e-commerce, online shopping has become very popular. While consumers enjoy the convenience brought by e-commerce, they are also deeply affected by the reputation fraud caused by the rapid development of e-commerce. At present, in e-commerce transactions, both sellers and buyers conduct transactions through the Internet. Buyers do not know the actual situation of the seller, nor can they see the real thing itself, and do not know whether the seller’s goods are good or bad. some information to judge. For consumers, the most important thing in shopping is to look at the seller's product description, the seller's reputation, and other people's evaluations of the items they want to buy. [0003] With the vigo...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a method and system for detecting swiping orders based on the characteristics of user behavior data, which can effectively prevent the existing anti-swiping methods based on order sales statistics or simple rules from identifying when dealing with increasingly professional means of swiping orders Defects such as low rate and easy failure

Images