Abnormal transaction identification method and device based on financial time series characteristics and readable storage medium

Abstract

The invention provides an abnormal transaction identification method and device based on financial time series characteristics, and a readable storage medium. A large amount of financial transaction flow information data to be detect which is suspected to be abnormal or relate to certain identified abnormal account numbers can be utilized, features of financial time series are extracted by neuralnetwork model adaptively, and then based on the operation of linear layer and softmax layer in a neural network, whether the trading account is pyramid selling account or not is classified and recognized. The abnormal transaction identification method provided by the invention can adaptively extracts financial time series features based on the SoftSeq2Seq-Attention neural network model, which to some extent reduces the investment of labor-intensive feature engineering. Through a single type of financial transaction flow data and fewer features, the method can achieve a good effect of abnormalfinancial account detection and recognition.

Description

technical field [0001] The invention relates to the field of financial transactions, in particular to a method for identifying abnormal transactions based on financial time series features, equipment and a readable storage medium. Background technique [0002] Abnormal financial transactions refer to financial transactions with abnormal circumstances or characteristics such as transaction amount, transaction frequency, and transaction location. Abnormal financial transactions include many fields, such as money laundering, credit card fraud, illegal fundraising, pyramid schemes, etc. Illegal pyramid schemes have always been one of the problems that need to be solved urgently in the field of financial security. Its essence is to realize the illegal transfer and accumulation of finance through the development of offline, disrupt the social and economic order, and endanger personal safety and social stability. Analysis of financial transaction data flow is an effective means to...

AI Technical Summary

Problems solved by technology

On the one hand, the pre-processing analysis of these various types of data will lead to more complex and labor-intensive feature engineering work

On the other hand, in the case of lack of data or incomplete MLM organization data, it is likely that the analysis results obtained by the identification method based on MLM network topology characteristics are not accurate enough and have low usability.

At present, there is no method that can combine the RNN neural network model to adaptively extract financial time series features for the identification of MLM financial accounts, thereby reducing or avoiding complex labor-intensive feature engineering work

Images