Tuesday 6th October, 2015
2:30pm to 3:20pm
In any language and all cultures, financial gain is the aim of most people. Unfortunately, many people (and companies!) resort to techniques that lie somewhere between immoral and criminal. Currently, many companies rely on a combination of external scoring services and internal manual fraud prevention procedures. This presentation will introduce ideas that are able to automate the detection of fraud and automate the analysis of new unknown fraud patterns.
Fraud detection is very specific to a particular domain. For example, credit card fraud is completely different to benefit fraud. This means that solutions must be bespoke and must fulfill the company's specific requirements. Mortgage fraud will be used as an example throughout this talk, although the techniques are applicable to any domain. It will discuss using software, databases and cluster computing frameworks to automate detection. It will also introduce the field of Machine Learning, with a particular focus on Deep Learning. Modern deep learning algorithms allow machines to analyze huge amounts of data to automate the discovery of new fraud vectors.
If you are thinking about implementing a fraud detection system for your business, and are interested in the cutting-edge of fraud detection technology, then this is the talk for you. Alternatively, feel free to visit me at the Trifork stand to talk about your specific domain. If you don't know what Machine Learning is and would like a buzzword-free introduction and example, this is also the talk for you.
Engineer at Trifork Leeds
Sign in to add slides, notes or videos to this session