Case: Van Lanschot

Successfully tackling money laundering with data science

In our PDEng program, our trainees join an organization for a year to devise a workable solution to a problem in which data science can play a decisive role. An example of such a problem is cybercrime in the banking world. Data science can be used successfully to combat money laundering and to recognize suspicious transactions.

A PDEng trainee from JADS researched large amounts of data at Van Lanschot, a bank in The Netherlands, and developed a model that can pinpoint such transactions.

Background Pattern

The challenge

“We were triggered by an article from JADS,”  says Paul Fleuren, responsible for the department that combats money laundering at Van Lanschot. “We were already using advanced data analytics to monitor our customer base, but looking for suspicious transactions is like looking for a needle in a haystack. How can this be done as effectively and efficiently as possible?”

What we did

A PDEng trainee researched the data and developed a tool that can analyze large amounts of data. This model can discover complicated transaction patterns that go beyond obvious criteria such as frequent transfers or very high amounts.

“What I actually did was model the various transactions as a network. I always connected the two parties involved in a transaction, the payer and the receiver. This resulted in a dataset that I analyzed in various ways. This resulted in a machine learning model that predicts the likelihood of anomalous transactions by a person or a group of people,” says Pallabi Sengupta, PDEng trainee at JADS.

The result

Fleuren is very pleased with the result, which will certainly help the fight against money laundering. “The model reveals complicated transaction patterns that an analyst would never consider. But we remain realistic. There is no holy grail, perfect systems that detect everything do not exist, it remains a journey of discovery. And crime is of course also constantly devising new strategies.”

Predicting the likelyhood of anomalous transactions

“I experienced the project as very satisfactory. ”

Pallabi Sengupta, PDEng JADS

Background Pattern

Revealing transaction patterns

“The collaboration with JADS was very pleasant. The model reveals complicated transaction patterns that an analyst would never consider”

Paul Fleuren, Van Lanschot

Background Pattern
startups in the JADS playground

Why partner up with JADS

JADS provides innovative data science programs at undergraduate, graduate and postgraduate level, conducts cutting edge data science research and offers great business opportunities with a continually growing ecosystem. From startups to SMEs and large corporates, our business partners gain access to talent, high level knowledge and business opportunities.

Partner up with JADS like 300+ other organizations and businesses and shape your data-driven future

Learn more about business opportunities
Group 5
Group 6
Group 7