The Institute for Information and Communication Technologies (IICT), HES-SO/ campus HEIG-Vd (www.heig-vd.ch), Yverdon-les-Bains, Switzerland, has an opening for a senior research data scientist to participate to the AFFUT (Advanced Analytics for Fraud Detection) project.
- PhD (evt. MSc) in applied mathematics (possibly related to data science), computer science, theoretical physics, statistics or related disciplines.
- Very good knowledge of Python, Java or a similar programming language
- Excellent publication record.
- Competitive remuneration package
- Opportunity to collaborate with Swiss, US and Korean researchers from reputable institutions and start-ups
The primary focus of the data scientist will be to perform research within the framework of a project in collaboration with NetGuardians, which regularly ranks among the most innovative Fintech start-ups in Europe but the future researcher will also be strongly encouraged to pursue and spend time for his own research.
In this project we want to investigate the use of machine learning methods (decision trees, deep neural networks and related approaches including unsupervised learning) for identifying banking fraud. This includes a comparative evaluation of the various approaches/algorithms, testing using real data provided by NetGuardians, improving and adapting the algorithms and a comparison in performance for each customer data. We would also like to enhance the above machine learning algorithms by the use of boosting techniques, which generally improve the accuracy and performance for imbalanced datasets (datasets of rare events, such as fraud occurrence). These methods will be implemented in the existing infrastructure of NetGuardians. A test of the tool will be performed in both a simulation environment and in real time for a selection of NetGuardians customers.
This is a 12-month position, eventually renewable. It must start at around June 2018 or later (depending on the availability of the candidate). A good working knowledge in English is required (no other language is needed). Applications, including a resume, a list of publications, and the name of at least three referees (physical and email addresses, phones numbers) should be sent as soon as possible to email@example.com (MS Word, .pdf, .ps or plain text).