Migrating Birds Optimization: A New Metaheuristic Approach
  • FENS
  • Migrating Birds Optimization: A New Metaheuristic Approach

You are here

IE-CS-MAT-OPIM Joint Seminar
Assoc. Prof. Ekrem Duman Ozyegin University (OzU)
December 12, 2012, Wednesday @ 13:40pm @ FENS L045
“Migrating Birds Optimization: A New Metaheuristic Approach and Its Application on QAP and Credit Card Fraud Detection”

Recently we proposed a new nature inspired metaheuristic approach based on the V flight formation of the migrating birds which is proven to be an effective formation in energy saving. Its performance is tested on quadratic assignment problem instances arising from a real life problem and very good results are obtained. The quality of the solutions are better than simulated annealing, tabu search, genetic algorithm, scatter search, particle swarm optimization, differential evolution and guided evolutionary simulated annealing approaches. The proposed method is also tested on a number of benchmark problems obtained from the QAPLIB and in most cases it was able to obtain the best known solutions. Later, the algorithm is applied to credit card fraud detection problem. The results obtained turned out to be the best among a set of algorithms including decision trees, support vector machines, neural networks, genetic algorithms and scatter search. We present these results in this talk.

This is joint work with Ali Fuat Alkaya, Mitat Uysal and İlker Eliküçük.
Ekrem Duman
Dr. Ekrem Duman has got his BS degree from Electrical and Electonics Engineering Department and MS and PhD degrees from Industrial Engineering Department, all from Bogazici University. Besides his current work as a faculty in the Industrial Engineering Department of Ozyegin University, he works on bringing solutions to complicated industrial problems. During this course, he has developed some specific and very successful generic solution procedures. Since 2005 he has conducted a number of projects using data analysis and optimization techniques, particularly for the financial sector. The models he developed include but are not limited to: marketing, customer loyalty and churn, customer lifetime value, application and behavioral scoring, Basel II AIRB approach, credit card and internet fraud detection, anti money laundering, ATM/branch location optimization and cash management, and social network analysis. Some of these projects involved international collaborations.