Anti-Money Laundering (AML) Software
This article explains some questions about Anti-Money Laundering (AML) Software including what it is, why is important, and some examples from this world.
Firstly, we can look at the meaning of money laundering.
Money laundering is legally defined as “transferring illegally obtained money through legitimate people or accounts so that its original source cannot be traced” (Black’s Law Dictionary 2009: 1097).
1. What is Anti-Money Laundering (AML) Software?
Anti-money laundering software is used by some companies to detect suspicious activities by persons (organizations) who are trying to produce income through illegal steps.
For example, banks and insurance companies analyze their customers and transactions in order to detect abnormal behavior patterns and activities that could be related to money laundering.
2. What are the companies in the AML Software ecosystem?
Generally, banks are in this ecosystem. Also, RegTech(Regulatory Technology) Companies and FinTech(Financial Technology) Companies are in the AML Software ecosystem.
Some of them:
Arctic Intelligence, AML Partners, Clarus Risk, Cognitive View, Compliance.ai, Encompass, Ecertic, Eventus, FacePhi, FeedStock, Fenergo, Hawk: AI, KYCGlobal, Red Oak, RailsBank, Starling, Token, Web Shield, Paypal, Transferwise, Deloitte, etc.
3. Which AI technologies are relevant to AML Software systems?
AI can take in disconnected risk signs across payment platforms, geographies, depositors, and payees, and connect the signals in meaningful ways.
- Reduction of false positives in the AML Process
Between the AI techniques that can reduce the rate of false positives, we can give the following examples:
Semantic analysis to identify correspondences triggered by redundant data.
Statistical analysis of customer information files to identify high-risk entities likely to represent a true positive result.
- Detecting the change in customer behavior
Machine learning models can be developed to help detect changes in customer behavior by analyzing their transactions.
- Analysis of unstructured data and external data
In external data, a traditional name search can find matches. Still, it can neither provide the context in which the name appears nor discern relationships with politically exposed persons (PEP) or high-risk entities or assess other risk indicators from these sources. Thus, natural language processing and AI techniques are necessary to analyze unstructured data and establish these connections.
- Robotic Process Automation (RPA) in AML and KYC
- Enrichment of alerts using external and internal data
- Generation of Natural Language in AML Compliance
4. Why are AML companies integrating AI in their solutions?
Technology experts, industry analysts, and financial institutions all agree that artificial intelligence is going to meaningfully help anti-money laundering (AML) compliance programs and outcomes.
AI-powered technology can reduce false positives, automate investigation processes, and streamline reporting in AML systems.
AI also decreases risk by finding financial crimes that current transaction monitoring systems (TMS) are missing.
5. What is the level of interest in integrating AI in AML systems?
There is a study about companies are currently using AI or not in the AML world. They asked some questions to 296 companies. According to this study:
We understood that from this study, the companies are on their way to adopting AI technologies for Anti-Money Laundering. More than a third (37%) of survey respondents say they are already using AI or other advanced analytics, while more than two-fifths (41%) expect to do so in the next 1–2 years. Only a small minority (3%) have no plans to introduce AI.
6. What are the benefits of using AI technologies AML?
AI for AML has been accepted and embraced in the industry and by regulators, the explainable technology is a safe investment.
Packaged AI solutions are easy to implement and can be fully operational within weeks.
AI for AML solutions can learn new financial crime patterns uncovered at one bank and, through “shared intelligence,” immediately identify the same patterns at other financial institutions.
7. How to evaluate modern AML systems in line with advances in AI?
There are critical components of a modern AML system. A Consolidated Backend, Unified Data, Advanced Analytics, and Improved Operations.
Here, the advanced analytics include those things:
· Machine Learning to Improve Detection (Machine learning models can improve detection by rapidly adapting to evolving trends.)
· Graph Analytics for Better Investigations (Graph analytics enables compelling, real-time visualizations of potential money laundering networks the AML investigators can explore to uncover otherwise hidden suspicious patterns.)
· Entity Resolution for a 360-Degree Customer View (360-degree picture of customers)
· Correlation to Build Better Cases (With machine learning to build better cases by correlating red flags and suspicious alerts from various systems into a single case, which the graph visualization of which can be used as an investigation tool.)
· Deep Learning to Find Patterns (Financial institutions can apply deep learning to graphs to find new graphs that are similar to previously identified graphs of criminal activity.)
· Natural Language Processing for Automatic Case Narratives (NLP can automatically generate case narratives based on what an investigator uncovers in graph visualization.)
· Collective Intelligence and Collective Learning for Recommendations (Financial institutions can use artificial intelligence to learn from previous case decisions about graph networks and provide recommendations or suggest the next steps to investigators.)
Improved Operations Include:
· Leverage Open Source Technologies (Apache Zeppelin and Jupyter notebooks, Apache Spark as an analytics engine, and popular data science languages such as R, Python, SQL, and Scala.)
· Consider Cloud
8. What are example case studies of companies using AI in their AML systems?
UOB, Tookitaki, and Deloitte prepared a machine learning pilot to accelerate the fight against money laundering.
An integrated ML platform for rapid development and deployment of models.
Here are a few ways that banks are applying these new approaches:
A Tier 2 US bank replaced 10 cash activity scenarios from its transaction monitoring system with a SAS neural network model and tripled SAR conversion rates while cutting monthly work items by 50%.
A Tier 1 global bank applied a random forest model with 200 trees to nearly 2 billion transactions, and in 10 minutes found 416 suspect entities that, on further triage, resulted in dozens of productive cases.
Another Tier 1 global bank used machine learning-driven automation to help automate due diligence document review, reducing the effort from two weeks of staff time to less than a minute.
An Asia Pacific bank turned to gradient boosting and deep neural networks to automate alert review and reduced false positives by 33%.
https://www.sas.com/en_us/insights/articles/risk-fraud/next-generation-anti-money-laundering.html
And also, there are some features of the AML software. From here, we can understand what kind of tools they have.
· FileInvite (Features: Investigation management, case management, compliance reporting, identity verification)
· Clear View KYC (Features: PEP screening, Watch list)
· ML Verify (Features: Bespoke document requests, Manage AML Policies & Procedures, automatically schedule client reviews, detailed event logging, digital ID checks, custom client portal for document upload, integrated with Companies House, automated PEP Searches, automated Financial Sanctions search)
· Biz4x by 4xLabs (Features: Transaction monitoring, PEP Screening, Watch list, Compliance reporting, Risk assessment, Identity verification)
· SAS Anti-Money Laundering (Features: Behaviour analytics, investigation management, case management, watch list, compliance reporting, risk management, SARs)
· Actimize (Features: Behaviour analytics, transaction monitoring, compliance reporting)
· AMLcheck (Features: Behavioural Analytics, Case Management, Compliance Reporting, Investigation Management, PEP Screening, Risk Assessment, SARs, Transaction Monitoring, Watch List)
· Token of Trust Identity Verification (Features: Behavioural Analytics, Identity Verification, PEP Screening, Risk Assessment, Transaction Monitoring, Watch List)
9. Which AML vendors have integrated AI in their solutions?
KYC2020, SAS, H2O AI, DELOITTE, SANCTIONSCANNER, QUANTRA VERSE, TRANSFERWISE, PAYPAL etc.
10. Bonus: A compelling topic to write about it :)
Maybe we can ask about that how robots can change this AML ecosystem?
Kindly note: I am new in the AML world. Please feel free to help me with this topic.
REFERENCES:
