Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Third-party platform payment fraud behavior online detection method based on LSTM

A detection method and behavioral technology, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve problems such as fund theft, inability to detect and identify new financial losses in real time, account theft, etc., and achieve strong fraud identification capabilities, The effect of reducing the risk of financial fraud and high accuracy

Inactive Publication Date: 2020-10-27
百维金科(上海)信息科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

While mobile payment brings great convenience to life, it also brings huge risks. There are a large number of fraudulent activities such as counterfeit applications, fund theft, and account theft.
The existing anti-fraud technologies of third-party payment platform companies are mostly applied to credit evaluation systems based on big data and pre-defined anti-fraud rules. There is still a certain lag in the practice, and it is impossible to detect and identify new types of fraud in real time and cause financial losses

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Third-party platform payment fraud behavior online detection method based on LSTM
  • Third-party platform payment fraud behavior online detection method based on LSTM
  • Third-party platform payment fraud behavior online detection method based on LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0032] LSTM-based online detection method for third-party platform payment fraud, combined with figure 1 As shown, it includes the following steps, step 1: data collection: including collecting basic information and historical behavior data of customer account registration from the back end of the third-party payment platform and obtaining real-time measurement point data from monitoring software; step 2: data preprocessing : Preprocess the collected data, includin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a third-party platform payment fraud behavior online detection method based on LSTM. The method comprises the following steps: acquiring data and preprocessing the acquired data; dividing the data into a training set and a test set; extracting main features according to the cumulative variance contribution rate CPV of the feature vectors; constructing an LSTM unit and an LSTM model, and using a mean square error as a loss function to update model parameters; and updating the weight and bias in the LSTM model by adopting an Adam gradient descent algorithm, optimizing themodel by using the test set, and finally deploying the optimized LSTM model to the rear end of the third-party payment platform to perform online anomaly detection monitoring on the account behavior of the customer. By implementing the technical scheme of the invention, the early warning result accuracy is high, the fraud identification capability is strong, the financial fraud risk is reduced, the timely system early warning can be sent out, and the account operation transaction can be blocked according to the risk level.

Description

technical field [0001] The invention relates to the technical field of risk control in the Internet financial third-party payment industry, in particular to an LSTM-based online detection method for third-party platform payment fraud. Background technique [0002] Under the concept of "Internet +", third-party mobile payment represented by Alipay and WeChat payment has developed rapidly. According to relevant reports, the transaction scale of third-party mobile payment reached 226.2 trillion yuan in 2019, a year-on-year increase of 18.7%. While mobile payment has brought great convenience to life, it also brings huge risks, such as a large number of fraudulent activities such as counterfeit applications, stolen funds, and account theft. The existing anti-fraud technologies of third-party payment platform companies are mostly based on big data credit evaluation systems and pre-defined anti-fraud rules. There is still a certain lag in the practice, and it is impossible to de...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q40/02G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06N3/045G06Q40/03
Inventor 江远强
Owner 百维金科(上海)信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products