Big data and machine learning – helping tackle cyber crime
Raffael Maio of NetGuardians
Feb 20, 2018
Raffael Maio, MD, APAC and co-founder, NetGuardians talks about software solutions his firms provides to financial institutions to detect and prevent any kind of fraud.
With a financial services industry increasingly reliant on technology, cyber-threats are a real, and for many organisations, persistent threat. There have been numerous examples of cyber-crime and internal fraud that have resulted in data leaks and/or financial losses. Firms are being required to be more vigilant when it comes to their technology, with greater pressure to improve both network resiliency and security. This is where firms like NetGuardians can assist, offering solutions to the industry to protect against fraud and cyber-crime. “We are helping to detect and reduce false positives and detect criminal activities via our innovative technology based on big data and machine learning” says Maio.
Maio and his associate started the firm ten years ago in Switzerland and have now expanded overseas with offices in Kenya, Poland and Singapore. They see the Asia region as a growing market and are planning to expand their team in-region so their clients’ needs can be fully addressed locally.
Maio says that their software product relies on three main pillars – machine learning, profiling and PBI. It can analyse massive amount of data and can also take in contextual information. “We run behavioural analysis to reduce false positives and increase true positives”. One of the things that draws clients towards NetGuardians is the tailored offerings provided for specific types of use cases such as e-banking fraud, SWIFT fraud to name a few, and their ability to quickly on board new clients, saving them some precious time.
Managing Director APAC, Co-founder at NetGuardians
More from Raffael Maio, NetGuardians
Latest Articles
Wealth Solutions & Wealth Planning
Robust Estate & Legacy Planning: The Need to Know Your Objectives and Choose Your Advisers Carefully