The AI method looks at sources including a user's profile, activities and social connections using what Vole dubs a supervised machine-learning environment that could automates the presently manual tasks of fraud detection.
So far, the results show the framework boosted fraud detection rates for particular account types by 68 percent with a five percent false positive rate.
According to a Volish report there are a few types of fraud relevant to Skype including, in particular, credit card fraud and other online payment fraud, as well as account abuse such as spam instant messages.
The idea of the system is to catch those fraudsters that elude the first line of defences at Skype.
Moises Goldszmidt, Yinglian Xie, Fang Yu, Martín Abadi of Microsoft Research and Anna Leontjeva of the University of Tartu, Estonia, conducted the research across 34,000 users that included a mix of legitimate and fraudulent accounts chosen from an initial randomised pool of 200,000 users that had not been blocked for more than four months since creating an account.
The research captured and analysed account habits of the captured Skype users limited to what communications methods they used and how often. The content of calls was not recorded and Skype usernames were anonymised.
It was possible to identify fraudulent accounts when inactive after four months but became hard to find if they remained active for more than 10 months after account creation. It would appear that most of the fraudulent accounts operating on Skype were hacked legitimate users.