References of "Stojanovic, Aleksandar 40080275"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailImproving Credit Card Fraud Detection with Calibrated Probabilities
Correa Bahnsen, Alejandro UL; Stojanovic, Aleksandar UL; Aouada, Djamila UL et al

in Proceedings of the fourteenth SIAM International Conference on Data Mining, Philadelphia, Pennsylvania, USA, April 24-26, 2014. (2014)

Previous analysis has shown that applying Bayes minimum risk to detect credit card fraud leads to better results measured by monetary savings, as compared with traditional methodologies. Nevertheless ... [more ▼]

Previous analysis has shown that applying Bayes minimum risk to detect credit card fraud leads to better results measured by monetary savings, as compared with traditional methodologies. Nevertheless, this approach requires good probability estimates that not only separate well between positive and negative examples, but also assess the real probability of the event. Unfortunately, not all classification algorithms satisfy this restriction. In this paper, two different methods for calibrating probabilities are evaluated and analyzed in the context of credit card fraud detection, with the objective of finding the model that minimizes the real losses due to fraud. Even though under-sampling is often used in the context of classification with unbalanced datasets, it is shown that when probabilistic models are used to make decisions based on minimizing risk, using the full dataset provides significantly better results. In order to test the algorithms, a real dataset provided by a large European card processing company is used. It is shown that by calibrating the probabilities and then using Bayes minimum Risk the losses due to fraud are reduced. Furthermore, because of the good overall results, the aforementioned card processing company is currently incorporating the methodology proposed in this paper into their fraud detection system. Finally, the methodology has been tested on a different application, namely, direct marketing. [less ▲]

Detailed reference viewed: 370 (34 UL)
Full Text
Peer Reviewed
See detailExploiting Long-Term Redundancies in Reconstructed Video
Stojanovic, Aleksandar UL; Ohm, Jens-Rainer

in IEEE Journal on Selected Topics in Signal Processing (2013)

Detailed reference viewed: 76 (4 UL)
Full Text
Peer Reviewed
See detailLight microscopy applications in systems biology: opportunities and challenges.
Antony, Paul UL; Trefois, Christophe UL; Stojanovic, Aleksandar UL et al

in Cell Communication and Signaling (2013), 11(1), 1-19

Biological systems present multiple scales of complexity, ranging from molecules to entire populations. Light microscopy is one of the least invasive techniques used to access information from various ... [more ▼]

Biological systems present multiple scales of complexity, ranging from molecules to entire populations. Light microscopy is one of the least invasive techniques used to access information from various biological scales in living cells. The combination of molecular biology and imaging provides a bottom-up tool for direct insight into how molecular processes work on a cellular scale. However, imaging can also be used as a top-down approach to study the behavior of a system without detailed prior knowledge about its underlying molecular mechanisms. In this review, we highlight the recent developments on microscopy-based systems analyses and discuss the complementary opportunities and different challenges with high-content screening and high-throughput imaging. Furthermore, we provide a comprehensive overview of the available platforms that can be used for image analysis, which enable community-driven efforts in the development of image-based systems biology. [less ▲]

Detailed reference viewed: 119 (12 UL)
Full Text
Peer Reviewed
See detailCost Sensitive Credit Card Fraud Detection using Bayes Minimum Risk
Correa Bahnsen, Alejandro UL; Stojanovic, Aleksandar UL; Aouada, Djamila UL et al

in 12th International Conference on Machine Learning and Applications (2013)

Credit card fraud is a growing problem that affects card holders around the world. Fraud detection has been an interesting topic in machine learning. Nevertheless, current state of the art credit card ... [more ▼]

Credit card fraud is a growing problem that affects card holders around the world. Fraud detection has been an interesting topic in machine learning. Nevertheless, current state of the art credit card fraud detection algorithms miss to include the real costs of credit card fraud as a measure to evaluate algorithms. In this paper a new comparison measure that realistically represents the monetary gains and losses due to fraud detection is proposed. Moreover, using the proposed cost measure a cost sensitive method based on Bayes minimum risk is presented. This method is compared with state of the art algorithms and shows improvements up to 23% measured by cost. The results of this paper are based on real life transactional data provided by a large European card processing company. [less ▲]

Detailed reference viewed: 269 (25 UL)
Full Text
Peer Reviewed
See detailCost sensitive credit card fraud detection using bayes minimum risk
Bahnsen, A. C.; Stojanovic, Aleksandar UL; Aouada, D. et al

in Proceedings - 2013 12th International Conference on Machine Learning and Applications, ICMLA 2013 (2013), 1

Credit card fraud is a growing problem that affects card holders around the world. Fraud detection has been an interesting topic in machine learning. Nevertheless, current state of the art credit card ... [more ▼]

Credit card fraud is a growing problem that affects card holders around the world. Fraud detection has been an interesting topic in machine learning. Nevertheless, current state of the art credit card fraud detection algorithms miss to include the real costs of credit card fraud as a measure to evaluate algorithms. In this paper a new comparison measure that realistically represents the monetary gains and losses due to fraud detection is proposed. Moreover, using the proposed cost measure a cost sensitive method based on Bayes minimum risk is presented. This method is compared with state of the art algorithms and shows improvements up to 23% measured by cost. The results of this paper are based on real life transactional data provided by a large European card processing company. © 2013 IEEE. [less ▲]

Detailed reference viewed: 240 (1 UL)