Anti-Money Laundering From False Positives to Real Positive with Predictive Modelling & Big Data

Anti-Money Laundering From False Positives to Real Positive with Predictive Modelling & Big Data

The False Positives

“If any financial crimes compliance people out there have just plugged in a monitoring system and think that they’re done   you’re going to be flooded with alerts without any context,” warned Bank of America’s Bill Fox .This explains why most banks have conversion rates that are more like 5-7% .Banks need to go beyond their monitoring systems so as to see impressive results in terms of efficiency as they need not hire large numbers of staff to sift through alerts from their monitoring systems. Hence the need to create an in-house system that compiles formation from different sources such as its monitoring reports, news reports, alerts issued by regulators, and far beyond & much more  & then turns that feedback into “events,”.

Challenges Ahead;

False positives and very low rate of conversion reflects the deficiency of the AML set up. Besides the stiff regulatory fines .The below will tell how soon the current system with a meagre 5 to 7 % conversion rate presently will become defunct;

1.    There are more than 5 billion cell phones. By 2020, experts predict there will be more than 50 billion connected devices.  Assuredly, criminals and criminal organizations will be attracted to this new financial and communications medium s as to leverage them

2.       With M-Payments will come  digital value smurfing to probably replace or at least out do   traditional money laundering, “smurfs” which places small amounts of illicit or dirty money into financial institutions in ways that do not trigger financial transparency reporting requirements. Dozens or even hundreds of digital smurfs could then be directed to transfer the value to accounts controlled by organized crime. 

3.    Law enforcement will be further challenged by issues such as venue, jurisdiction and competency. The expertise to systematically track M-Payments simply does not exist.  A lack of physical evidence further handicaps law enforcement investigations, as there may not be any cash or money equivalents to monitor or seize.  If the conveyor or recipient phone is destroyed, it may be impossible to reconstruct or determine the information that was on the phone. Here the mortar branch ceases to exist.

4.    Today's trade-based money laundering activity goes beyond traditional laundering of criminal funds to include terrorist financing and intentional efforts to circumvent international sanctions, “Criminals turn to this as it's a classic needle in a haystack — an $18.3 trillion business formed of a "web of complexity that involves finance, shipping and insurance interests operating across multiple legal systems, multiple customs procedures, and multiple languages, using a set of traditional practices and procedures that in some instances have changed little for centuries . This state of affairs is exacerbated by a number of factors, especially the lack of data sharing between customs, tax and legal authorities and a tendency to rely on AML procedures designed to target cash smuggling and financial system misuse. 

5.    While key players in terrorist networks may be identified by the international community as terrorists, many of the lower-level, tenuously-connected contributors to terrorist networks remain unknown. These low-level contributors, prompted by group actions which mimic popularized crowd funding strategies have become another source of financing and physical resources for ISIL. Social media platforms unintentionally provide an effective method for terrorist groups and their sympathizers to exploit this technology for terrorist financing purposes.

6.    A symbiosis is developing between organized crime and terrorist organizations. Sharfuddin Memon, director of a Karachi citizens’ crime watch group, described the motivations behind this activity: “The world thinks this is about religion, but that’s a mistake.  It’s about money and power.  Faith has nothing to do with it.”

The Way Ahead

The new innovations also provide platforms to criminals as well which the current system will most certainly will not be able to cope with .So the need to extract and analyze in-house and external data, both structured and unstructured as the illegal process is all about taking ‘dirty’ money and making it ‘clean’ passing funds through an intricate and interconnected network of people, places & things and their inherent but otherwise unseen interconnections. The current approach and the AML solutions which solely focuses on entity-level (person, business, corporation) or transaction level risk scores, without viewing them within the context of the greater network risk score.

At the same time a myriad of business data exists. Communications and social media are growing exponentially. Industry calls these massive data bases, “big data."  Concurrently, there have been major advances in data mining and advanced analytical capabilities that can help organizations derive the “intelligence” from this vast amount of data.  Data warehousing and retrieval are enhanced by cutting edge technologies that search, mine, analyze, link, and detect anomalies, suspicious behaviors, and related or interconnected activities and people.

The good news began in 2009 with the invention of ‘Spark’ (by UC Berkeley ) which is  a powerful open source processing engine built around speed, ease of use, and sophisticated analytics. Spark is a general-purpose engine used for many types of data processing. ‘Spark’ comes packaged with support for ETL, interactive queries (SQL), advanced analytics (e.g. machine learning) and streaming over large datasets. For loading and storing data, Spark integrates with many storage systems (e.g. HDFS, Cassandra, HBase, S3). Spark is also pluggable, with dozens of third party libraries and storage integrations. Additionally, Spark supports a variety of popular development languages including Java, Python and Scala.( https://databricks.com/spark/about)

In furthering this crucial piece of innovation Tresata and Databricks announced this March a real-time, Spark and Hadoop-powered Anti-Money Laundering solution earlier today. Tresata’s predictive analytics application TEAK, offering for the first time in the market an at-scale, real-time AML investigation and resolution engine leveraging ‘Spark ‘.It is certified to run on Databricks Cloud, Tresata’s TEAK is breaking new ground and offering Banks, Retailers, Telcos & Regulators the only quick start, rapidly scalable AML solution.

Hope this is a harbinger of an era where ‘false positives’ is a term of the past making the regulatory burden more meaningful .At least meaningful to the extent that Banks don’t get the hit of ‘Reputational Risk’ and the billions of dollars  outflow accounted to penalty.

That in effect frustrates the crime & terror networks.