Deep anti-money laundering detection system can significantly decrease the time and increase the precision of transaction monitoring – a routine task requiring much knowledge and experience.
Could financial institutions serve their customers better simply by asking them fewer questions - but still know just as much as they should to do their jobs exceptionally well? What if lots of answers to the customers' questions would already be there?
That's where AI comes into picture. It will change everything, finance included. And this is why 90 perc. of what we do is strictly related to AI, more specifically: to deep learning, i. e. the use of neural networks for making decisions.
AI is sort of like the equivalent of the flying shuttle, one of the key developments in the industrialization of weaving during the early Industrial Revolution. And just as John Kay's invention has doubled the productivity of weavers and reduced the need for manpower, AI can help humans in many tedious mental tasks. Credit scoring, claims adjustment, or money laundering detection – deep learning is useful in all situations where there is a specific action pattern to follow, coupled with situation assesment based on expertise.
Deep learning technology optimizes the existing anti-money laundering processes by significantly enhancing the effectiveness of most commonly used – and inefficient – rule-based approaches, characterized by high false-positive rates and unable to consider complex interdependencies between various activities carried out to launder money. Comarch Anti-Money Laundering makes investigating suspicious activities simpler, faster and more effective by reducing the number of false alarms and minimizing risk of false negatives through the use of advanced supervised and unsupervised deep learning techniques such as classification or anomaly detection.
Knowledge on customer needs can be found in the data depicting their past decisions, behaviors and preferences. Over time, a banking application learning the customer requirements becomes a personal advisor – it can analyze financial capabilities, select solutions, or anticipate future needs. This "deep insight" into customer data is possible thanks to neural networks. Not only are they based on data analysis but, more importantly, on drawing conclusions from the analysis, which reflects the process occurring in the human brain. Deep learning engines are also able to organize, on a daily basis, the employee’s entire to-do list, recommending the next best course of action – for the sake of productivity.
Human beings have a natural ability to recognize objects. Currently, this ability is shared by machines built upon convolutional networks, specialized in processing images. And recognizing objects can be applied in various ways in finance. Imagine being able to find houses for sale in the area where you are now - with all necessary information on them, and a loan one tap away. Launch the camera in your smartphone, switch to panorama view, and you will see virtual sale offers attached to real buildings. That’s what augmented reality and deep learning combined is like.

Latest news

Virtual Reality

Comarch Brings Another Level Of Digitalization In Wealth Management

As the world is slowly being captured by digitalization, from physically buying stuff to now just buying everything online, opting for financial services online, is not far behind. Introducing Comarch, a provider of IT and software systems, that is based.
Virtual Reality

This is your new virtual reality

It’s on. VR is here to stay in the entertainment world. Soon it will become a part of our everyday life. And over time it might just blend with the meatspace to the point where we won’t be able to tell both realities apart


Questions? Suggestions? Whatever is on your mind - drop us a line!