3 Things to look for in a Transaction Monitoring System

By Abi Solomon 1 week agoNo Comments
Home  /  Uncategorized  /  3 Things to look for in a Transaction Monitoring System

Do you remember your first car? The one that was about ten years old and struggled to keep up with the other cars on the highway. It probably gave you trouble with the starter, brakes, transmission, and air conditioning. The only thing in the car you could rely on was the radio, which blasted music as you sputtered down the road.

Despite all its flaws, those cars are tough to replace. You probably drove it until your auto repair guy said there was nothing he could do to keep the engine running.

 And so, you bought or leased something new, and it completely changed your driving experience. You were no longer worried, every time you drove, that you might end up stopped on the side of the road with a plume of smoke coming out of from the hood.

 The new car made you  realize how  terrible your old car was and convinced you that you were never going back.

That car experience came to mind while talking with a potential client. The difference between AI and rule-based transaction monitoring is about the same between driving a Model T and cruising in an SUV. One sputters, pushing compliance officers in every direction to investigate false positives. The other drives ahead smoothly, letting you know when there is something  concrete worth investigating

For banks and PSPs looking to upgrade their monitoring capabilities, here are three things to consider when  looking for your next platform.

AI Is a Must Have

Trying to fight money laundering without using Artificial Intelligence (AI) is like bringing a water gun to a duel. Banks and PSPs will be badly overmatched and have little likelihood of success.

There are simply far too many transactions for any group of people to monitor on their own, and other tools have proven ineffective.

AI can increase the accurate detection of fraud. Its strengths lie in pattern recognition and connecting seemingly disparate data points. These play into the needs of financial institutions, as AI is capable of looking not only for known money laundering typologies but can also recognize when financial behaviors deviate from the norm.

There was some concern in the past, particularly among banks, that using AI will put them in a difficult position with regulators. When rule-based transaction monitoring was in place, they could easily show the regulator what they were looking for and explain their decision-making process.

AI is a different story. The technology is far more difficult to explain, as decisions deviate from the hard-coded rules and may not even be reproducible. Banks that are questioned by regulators will be hard-pressed to explain what happened since they are reliant on technology that they don’t necessarily understand.

However, regulators recognize the position of banks and have been accepting of the technology to some degree for some time.

Rob Gruppetta, head of financial crime in UK’s FCA, spoke at a FinTech Innovation in AML event in 2017 and told participants that AI was capable of aiding the fight against money laundering, and could be used to match photos in identity documents, as well as to identify customers that pose a high risk.

In December 2018, five major US regulators, including FDIC and FinCEN, issued a joint statement to “encourage to consider, evaluate, and, where appropriate, responsibly implement innovative approaches to meet their Bank Secrecy Act/anti-money laundering (BSA/AML) compliance obligations, in order to further strengthen the financial system against illicit financial activity.”

The statement went to say “Some banks are also experimenting with artificial intelligence and digital identity technologies applicable to their BSA/AML compliance programs. These innovations and technologies can strengthen BSA/AML compliance approaches, as well as enhance transaction monitoring systems. The Agencies welcome these types of innovative approaches to further efforts to protect the financial system against illicit financial activity. In addition, these types of innovative approaches can maximize utilization of banks’ BSA/AML compliance resources.”

The momentum has been pushing in favor of AI, and any transaction monitoring tool that isn’t based on AI will have limited functionality and will need to be replaced in the near future.

Cloud vs On-Premises Solutions

In many ways, when viewed through a transaction monitoring lens, the financial industry is split into two very distinct groups. The first group being banks and other traditional financial organizations that are highly regulated. They keep their data on-premises, protecting it against cyberthreats and other criminals.

The second group includes FinTechs who are far more open to adopting cloud-based technology. They primarily exist on the internet, and their comfort level with technology is far more advanced than the banks.

When looking for a solution, it is critical that the vendor understands the concerns and regulatory requirements of your organization, as well as its cultural needs. While some solutions can be deployed either on-prem or on the cloud, others are limited to one or the other. When searching for your next transaction monitoring system, make sure that your vendor can deliver the platform that meets your needs.

Preparing the Data

Every transaction monitoring system feeds on data. It analyzes the information it receives, and issues alerts when different criteria are met. However, the data that the different platforms ingest can be significantly different.

Some transaction monitors are capable of reading raw, unprocessed data. This can make the whole process run more efficiently, as data can be fed directly from the source into the transaction monitoring system. This eliminates any type of lag, as the system can start analyzing the SWIFT messages or other source material immediately. In effect, analysis takes place in near real-time.

Other systems require the SWIFT messages to be processed in some fashion. They need to be reformatted in some way to enable the transaction monitoring platform to read and understand the data.

Processing the data can cause some delay and makes it more difficult to react in real-time to questionable transactions. It also adds additional steps into the process, which introduces additional levels of risk.

For financial institutions that require near real-time monitoring, their system must be able to work with raw data. There is an elegant efficiency in the process, which allows it to run more smoothly. For organizations where real-time monitoring isn’t vital, or they are comfortable with the extra steps involved in processing the data, finding a solution that uses raw data isn’t as critical.

Upgrading Your Transaction Monitoring

Banks and PSPs are under intense pressure to upgrade their transaction monitoring tools. Look for a system that runs on AI, offers the set-up that works for your organization, and can utilize raw data that allows you to effectively and efficiently monitor transactions.

this post was shared 0 times

Leave a Reply

Your email address will not be published.