# Working with Both ‘Human’ AI and Graph Technology to Combat Money Laundering
Author:  Pal Sinha, Barnali 
Author URL: https://financedigest.com/author/pal-sinha-barnali
Published: 2021-03-15
Category: TECHNOLOGY
Category URL: https://financedigest.com/category/technology
Meta Title: Graph Technology & Human AI: The Answer to Money Laundering
Meta Description: Discover how graph technology and AI can help financial institutions combat money laundering by uncovering intricate networks of illegal activity and
URL: https://financedigest.com/working-with-both-human-ai-and-graph-technology-to-combat-money-launderinghtml

![undefined](https://prod.superblogcdn.com/site_cuid_cm5qst7v3003gwirgwqtxn8i8/images/just-2-1736838526824-compressed.jpg)

_By **Amy Hodler,** Director, Analytics and AI Program_ _at_ [_Neo4j._](https://neo4j.com/)

_Graph technology and ‘Human’ or explainable AI may provide the answer to money laundering, says Neo4j’s Amy Hodler_

Money laundering, defined by the FBI as the process by which criminals disguise their illegal gains to make them appear to have come from legitimate sources, is a huge global problem. In the UK alone, it costs [more than £](https://www.nationalcrimeagency.gov.uk/news/national-economic-crime-centre-leads-push-to-identify-money-laundering-activity#:~:text=Money%20laundering%20costs%20the%20UK,reaching%20consequences%20for%20us%20all) [100 billion](https://www.nationalcrimeagency.gov.uk/news/national-economic-crime-centre-leads-push-to-identify-money-laundering-activity#:~:text=Money%20laundering%20costs%20the%20UK,reaching%20consequences%20for%20us%20all) [a year](https://www.nationalcrimeagency.gov.uk/news/national-economic-crime-centre-leads-push-to-identify-money-laundering-activity#:~:text=Money%20laundering%20costs%20the%20UK,reaching%20consequences%20for%20us%20all). The UN estimates the amount of money laundered globally stacks up to 5% of global GDP [or US](https://www.unodc.org/unodc/en/money-laundering/overview.html) [$2 trillion](https://www.unodc.org/unodc/en/money-laundering/overview.html) per year.

No-one doubts the severity or scale of the money laundering issue. Successfully combatting money laundering, however, involves following illegal money trails, which is not easy. Financial criminals are clever, and cyberspace gives them many places to disappear. Money launderers are adept at creating an intricate network of identities and accounts to funnel their illegal efforts. The subterfuge makes it challenging to find their breadcrumb trail buried inside legitimate transactions which flow through [banking networks](https://www.financedigest.com/could-the-npa-be-the-catalyst-banks-need-to-transform-their-payment-networks.html "Could the NPA be the catalyst banks need to transform their payment networks?") every second.

Financial [institutions](https://www.financedigest.com/top-5-security-technologies-that-every-finance-institution-workplace-should-consider.html "Top 5 Security Technologies That Every Finance Institution Workplace Should Consider") need to know exactly where funds are coming from and where they are going at all times. One reason standard AML (anti-money laundering) [falls short](https://www.financedigest.com/analysis-china-property-financing-tweaks-fall-short-of-investor-expectations.html "Analysis-China property financing tweaks fall short of investor expectations") is that it typically monitors for deviation from standard banking patterns in discrete data and transactions. The technique does not [detect the shared characteristics that typify money laundering networks](https://www.financedigest.com/closing-the-door-before-the-horse-bolts-developing-a-proactive-network-detection-and-response-ndr-strategy.html "Closing the door before the horse bolts: Developing a proactive network detection and response (NDR) strategy "). Furthermore, such discrete methods tend to issue a lot of [false positives](https://citywireselector.com/news/dirty-money-nordea-am-puts-money-laundering-on-esg-watch/a1222185), which harm customer relationships. And when standard AML systems do look at networked data, they can’t scale up that well. It can also take from 20 minutes to several hours to investigate and resolve complex alerts.

![Amy Hodler](https://prod.superblogcdn.com/site_cuid_cm5qst7v3003gwirgwqtxn8i8/images/amyhodler-450x565-1736838527053-compressed.png)

Amy Hodler

The main reason why conventional approaches to anti-money [laundering](https://www.financedigest.com/the-problem-with-current-anti-money-laundering-processes-a-lack-of-context.html "The problem with current Anti-Money Laundering processes: A lack of context") are not operationally practical is that most anti-money laundering systems are based on a relational database model. A relational model means that [data is stored in predefined tables and columns, which is suited to some business applications—but with large, unstructured data sets](https://www.financedigest.com/byd-set-to-be-chinas-top-selling-car-brand-for-nov-tesla-gains-data.html "BYD set to be China’s top-selling car brand for Nov, Tesla gains -data"), this kind of data representation can rapidly hit the buffers. Even the most promising AML investigation ends up being too complicated, and response times are too slow.

These older AML [solutions are trying to detect fraud in the absence of real](https://www.financedigest.com/the-professionals-at-real-estate-funding-solutions-helping-you-find-success-with-commercial-real-estate-loans.html "The Professionals At Real Estate Funding Solutions Helping You Find Success With Commercial Real Estate Loans") context. What governments, [banks and financial institutions need](https://www.financedigest.com/why-banks-need-to-embrace-ai-first-customer-service.html "Why Banks Need to Embrace AI-First Customer Service") is the ability to follow a trail from one account to another. This requires having a 360-degree view of the intricate complexity of the money laundering network to determine how assets and individuals are related.

**_A relationship-centric approach_**

While no measure can be 100% bulletproof, significant opportunity for [anti-money laundering](https://www.financedigest.com/are-compliance-and-anti-money-laundering-aml-regulations-hurting-your-sales.html "Are compliance and anti-money laundering (AML) regulations hurting your sales?") improvement can be achieved. A technique many practitioners, including some of the world’s leading banks, are using is graph database technology and AI.

Graph technology was the approach used in the world’s biggest investigations of the offshore financial industry, the [FinCEN Files, Panama and Paradise Papers](https://www.icij.org/blog/2018/07/how-icij-deals-with-massive-data-leaks-like-the-panama-papers-and-paradise-papers/). If it wasn’t for graph databases joining the dots between the hidden relationships, the investigations would not have recouped the [more than $1.2 billion in resulting fines and back taxes](https://www.icij.org/investigations/panama-papers/panama-papers-helps-recover-more-than-1-2-billion-around-the-world/?utm_source=ICIJ&utm_campaign=11e3c89505-0403_WeeklyEmail&utm_medium=email&utm_term=0_992ecfdbb2-11e3c89505-82515213). The International Consortium of Journalists (ICIJ), the group behind the examinations, has just been nominated for a Nobel peace prize for the string of graph-powered investigations it started in 2011.

Graph technology’s underlying computer architecture is the key reason it is so helpful with AML work. In contrast to relational databases, graphs interpret individual data such as ‘person’, ‘account’, ‘company’, ‘address’, and their relationships with one another, like ‘registered at’, or ‘transacted with’. The data model accurately portrays even really complex relationships. Such a relationship-centric approach enables the AML investigator to better manage, read and visualise their data, giving [money laundering teams a trackable and in-depth picture of assets and the relationships between people](https://www.financedigest.com/more-than-twice-as-many-consumers-trust-customer-reviews-over-companies-themselves-according-to-research-from-smart-money-people.html "More than twice as many consumers trust customer reviews over companies themselves according to research from Smart Money People"). Moreover, graph databases are supremely fast at exposing patterns, providing financial institutions real-time insight into their assets and associated relationships.

The great advantage of graph database technology is that any number of qualitative or quantitative [properties can be assigned to data](https://www.financedigest.com/simplifying-home-insurance-through-property-characteristics-data.html "Simplifying home insurance through property characteristics data"), showing complex relationships coherently and descriptively. One of the best-known graph algorithms for potentially thwarting money laundering is ‘PageRank’. This [machine learning](https://www.financedigest.com/transforming-insurance-through-artificial-intelligence-and-machine-learning.html "Transforming Insurance Through Artificial Intelligence and Machine Learning") algorithm measures transitive influence or connectivity between nodes or objects. It can uncover objects based on their additive relationships and rank nodes with a relative score. For AML in financial institutions, graph [technology can identify important or influential customers](https://www.financedigest.com/verasity-joins-the-brightcove-marketplace-to-provide-customers-with-proprietary-ad-tech-technology.html "Verasity Joins the Brightcove Marketplace to Provide Customers With Proprietary Ad-Tech Technology") who head up countless transactions. Nodes with a high PageRank score can be illustrated using a visualisation tool to appear larger in the view and can be easily and rapidly isolated.

Another key graph algorithm is ‘Weakly Connected Components’, designed to reveal the hidden [networks that inform a money laundering trail based on features such as multiple companies](https://www.financedigest.com/hackers-hit-italian-oil-company-enis-computer-networks.html "Hackers hit Italian oil company Eni’s computer networks") that appear to be registered at the same address. Pinpointing connections like these allows analysts to identify suspicious activity.

Compliance experts Kerberos comments on the use of graph-based AML, “Instead of taking a superficial look at relationships, \[our\] legal experts can also uncover relationships only apparent at the second or third level.”

**_Human AI offers insight_**

AML start-up, Iceland’s [Lucinity](https://lucinity.com/), uses what it calls [a ‘human AI’ approach](https://www.youtube.com/watch?v=Yj9s3bXNa3Y) to help the firm’s many AML clients create 360-degree views of the actors and transaction networks that banks need to monitor.

Lucinity’s leadership [explain](https://www.financedigest.com/explainer-scientists-investigate-hepatitis-outbreak-in-children-in-europe-and-us.html "Explainer-Scientists investigate hepatitis outbreak in children in Europe and US") that “Investigators are not only seeing exactly why the algorithm determined something is a case of money laundering, the system can tell them exactly what money laundering the bad actor is doing, what behaviour they are exhibiting, and why the algorithm flagged the case.” There is also a feedback element from the investigators so that the algorithm can be fine-tuned. The [firm says](https://www.financedigest.com/over-a-dozen-chinese-based-firms-say-they-have-minimal-exposure-to-svb.html "Over a dozen Chinese-based firms say they have minimal exposure to SVB") if the AML AI doesn’t get feedback and intellectual knowledge from humans, it can’t improve.

Unless we can analyse [data relationships effectively](https://www.financedigest.com/can-banks-compete-in-the-digitisation-race-without-effective-data-integrity.html "Can banks compete in the digitisation race without effective data integrity?") and in real-time, we will have little chance of uncovering the criminals who continue to launder their dirty money in the world’s financial reservoirs.

Graph database software and AI approach promise to unlock the money laundering puzzle to help the [banking system fight back](https://www.financedigest.com/canadian-banks-fighting-brokers-back-for-customers.html "Canadian Banks Fighting Brokers Back For Customers").

_The author is_ _Director, Analytics and AI Program_ _at_ [_Neo4j_](https://neo4j.com/) _, the world’s leading graph database company. She is also co-author of_ [_Graph Algorithms: Practical Examples in Apache Spark & Neo4j_](http://neo4j.com/graph-algorithms-book/?ref=pr-) _, published by O’Reilly Media_


---
This blog is powered by Superblog. Visit https://superblog.ai to know more.
---