Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Anti-money laundering system and method based on machine learning

A machine learning and data system technology, applied in machine learning, instruments, finance, etc., can solve the problems of anti-money laundering system, such as poor timeliness, inability to intercept in real time, and unstable detection accuracy, so as to reduce manpower and time costs and realize Real-time detection and improvement of the effect of the effect

Active Publication Date: 2021-03-26
SICHUAN XW BANK CO LTD
View PDF18 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the poor timeliness of the anti-money laundering system in the prior art, the inability to intercept in real time, the unstable detection accuracy, and the waste of manpower for detection, the present invention provides an online real-time anti-money laundering system and method based on machine learning, the purpose of which is to : Improve the identification accuracy and coverage of money laundering strategies, identify and block money laundering transactions in real time, and reduce labor and time costs for money laundering detection

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
  • Anti-money laundering system and method based on machine learning
  • Anti-money laundering system and method based on machine learning
  • Anti-money laundering system and method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] An online real-time anti-money laundering system based on machine learning, characterized in that it includes:

[0056] Time series feature processing layer: construct time series features based on user information;

[0057] Distributed model operation layer: Based on the time series characteristic data, build a money laundering model, and integrate the money laundering model result set;

[0058] Real-time strategy layer: Based on the money laundering model result set, construct a money laundering strategy set;

[0059] Decision-making level: Integrate new information from policy sets to make anti-money laundering decisions

[0060] The time series feature processing layer builds time series features based on the transferred user information and data, and processes the time series features in three modes, and transfers the processed time series features to the distributed model operation layer, which is based on the time series The characteristics of the model are cal...

Embodiment 2

[0062] Embodiment 2: The decision-making layer is connected to an anti-money laundering verification system, and the anti-money laundering verification system connected to the decision-making layer can manually verify suspicious transactions provided by the anti-money laundering system, and further detect money laundering transactions.

Embodiment 3

[0063] Embodiment 3: The anti-money laundering verification system is connected to the anti-money laundering verification data system, the anti-money laundering verification data system is connected to the anti-money laundering data system, and the anti-money laundering data system is connected to the sequential feature processing layer. The anti-money laundering verification system transfers the manually verified data into the anti-money laundering verification data system, and the anti-money laundering verification data system transfers the anti-money laundering verification data into the anti-money laundering system. Through the above data closed loop, the coverage of the anti-money laundering data system is increased, enabling The timing feature selection of the timing feature processing layer is more extensive and targeted.

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 discloses an anti-money laundering system and method based on machine learning, belongs to the field of artificial intelligence anti-money laundering, solves the problems that in the prior art, an anti-money laundering system is poor in timeliness, cannot intercept money in real time, is unstable in detection accuracy and wastes detection manpower. The system comprises a service system and an aging characteristic processing layer connected to the lower portion of the service system. The timeliness characteristic processing layer is connected with the distributed model operation layer, the distributed model operation layer is connected with the real-time strategy layer, the real-time strategy layer is connected with the decision-making layer, the decision-making layer is connected with the service system and the anti-money laundering checking system, the anti-money laundering checking system is connected with the data system, and the data system is connected with the timesequence characteristic processing layer to form a data closed loop. The money laundering strategy recognition precision and the money laundering strategy recognition coverage are improved, money laundering transaction is recognized in real time and blocked, and the labor cost and time cost of money laundering detection are reduced.

Description

technical field [0001] The invention belongs to the field of intelligent money laundering monitoring, in particular to an online real-time anti-money laundering system and method based on machine learning. Background technique [0002] Anti-money laundering and anti-terrorist financing have risen to national strategies and become an important tool to deal with national non-traditional security affairs. Since 2012, the Anti-Money Laundering Financial Action Task Force (FATF) has made comprehensive revisions to anti-money laundering international standards and assessment methods. The connotation of anti-money laundering has been expanded to include anti-money laundering, anti-terrorist financing and anti-weapons of mass destruction proliferation financing. Broader fields such as the Internet of Things are no longer limited to simple technical affairs, but are closely bound up with international political games, rising to the level of national strategy, and becoming the country...

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): G06Q40/04G06Q50/26G06N20/00
CPCG06Q40/04G06Q50/26G06N20/00Y02P90/30
Inventor 王萍贾坤
Owner SICHUAN XW BANK CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products