Ph.D. candidate

The University of Luxembourg seeks to hire outstanding PhD candidates at its Interdisciplinary Centre for Security, Reliability and Trust (SnT ).

SnT is a recently formed centre carrying out interdisciplinary research in secure, reliable and trustworthy ICT (Information and Communication Technologies) systems and services, often in collaboration with industrial, governmental or international partners. The Centre is currently expanding its research activities and is seeking highly motivated candidates who wish to pursue research in close cooperation with our partners leading to a PhD. For further information you may check: www.securityandtrust.lu . The PhD project will be conducted in partnership with CETREL ( www.cetrel.lu ). CETREL, a trusted partner of the Luxembourgish financial market, is expert in management of automated payment systems and automated banking and e-banking operations, and is a specialist in establishing and operating IT infrastructures and highly secure IT communication.

Offer The University offers a three year appointment (extension up to 4 years in total is possible). The University offers highly competitive salaries and is an equal opportunity employer. You will work in an exciting international environment and will have the opportunity to participate in the development of a newly created research centre.

Project description The PhD project concerns fraudulent transaction patterns in the financial sector. It aims at studying how to implicate adaptive reasoning in the design of an automatic detection system and how to benefit from/apply latest achievements of the research field of machine learning. The objective is to define and to implement a predictive model on a mathematical basis, which makes sure an understanding of interdependencies within transaction parameters of single and multiple cardholders is reached. Important aspects will be a concrete contribution with respect to the reduction of false alarms (false positives, false negatives), the consideration of statistical manifold learning, and statistical optimization. The focus will initially be on off-line processing and benchmarking performance against existing techniques; also, suitable performance measures will be investigated and compared. Successfully tested methods will be optimized or directly used by CETREL for a real-time implementation.

Keywords

• Fraudulent Transaction Patterns in the Financial Sector
• Machine Learning
• Prediction
• Statistical Manifold Learning.

• Master's degree - or equivalent - in Computer Science, Applied Mathematics, or a comparable field.
• Strong programming skills, preferably in C/C++, as well as excellent skills in Machine Learning, Pattern Recognition, and Data Mining are required.
• Experiences in the retrieval and management of massive data sets are considered as a plus.
• Very good written and oral English skills.

• Cover letter motivating your interest for this position.
• Curriculum Vitae including your academic career and a list of publications and talks.
• Academic transcripts.
• Research statement and topics of particular interest to the candidate (300 words).
• Two recommendation letters and/or contact information to at least two referees.

TO: snt-jobs@uni.lu
CC: christoph.schommer@uni.lu;   djamila.aouada@uni.lu
SUBJECT: PhD in Pattern Recognition

Applications will be handled in strict confidentiality. For further inquiries, please contact Prof. Björn Ottersten ( bjorn.ottersten@uni.lu ), Prof. Christoph Schommer ( christoph.schommer@uni.lu ) or Dr. Djamila Aouada ( Djamila.aouada@uni.lu ).

The call is open until October 21, 2011.