Welcome to the business of certainty. When you need to understand the companies in your ecosystem, you’ll benefit from a certain approach. We capture and treat private company information for better decision making and increased efficiency.
Machine learning aids fight against money laundering
If recent developments in Australia are anything to go by, innovation in the fields of machine learning and artificial intelligence could play an increasingly important role in anti-money laundering efforts in the future.
Research in this area is being led by the Australian Transaction Reports and Analysis Centre (AUSTRAC), the country's financial intelligence agency. AUSTRAC takes regulatory responsibility for combating money laundering and terrorism financing.
In Australia alone, criminals are thought to launder approximately US$4.5 billion (£3.4 billion/AU$5.9 billion) every year. On a global level, the figure is closer to US$1.5 trillion.
The UK is among the countries that have adopted a tougher stance and launched fresh efforts to tackle this problem in recent times, but one of the challenges regulators and law enforcement agencies face is the increasing sophistication of criminal methods.
Large cash payments and properties being bought and quickly sold on are common warning signs of money laundering, but these practices are becoming less common.
Pauline Chou at AUSTRAC told New Scientist that money launderers are getting better at making their transactions appear innocuous.
Furthermore, the sheer number of transactions taking place makes detailed analysis extremely difficult. In Australia, for example, up to 100 million transactions take place every year.
Ms Chou said: "It's just become harder and harder for us to keep up with the volume and to have a clear conscience that we are actually on top of our data."
This is where machine learning comes in. AUSTRAC collaborated with researchers at RMIT University in Melbourne to create a system capable of detecting signs of suspicious activity within huge amounts of data.
The technology, which was trained using previous analyses of suspected money laundering networks, narrowed down millions of transactions to around 750,000 cases for further analysis by human investigators.
It is also capable of identifying patterns by viewing transaction histories across groups, rather than focusing on individuals.
Praising the work AUSTRAC has done in this area, Jason Kingdon, who has worked on AI to root out fraud and insider trading on the London Stock Exchange, said the agency is "doing something new".
Certainty is a highly-prized commodity in business. Data might be getting bigger all the time, but this only makes extracting value from it more difficult.
In capturing and treating private company information we aim to give you more certainty –
and help you make better decisions and work
Our solutions are designed to help different business challenges and streamline your workflow. Many of our customers blend our information with their own internal data to get a more complete picture of the companies in their ecosystem.
Try our more certain approach – welcome to the business of certainty.