|
Title:
|
PROFIT-BASED LOGISTIC REGRESSION TRAINED BY MIGRATING BIRDS OPTIMIZATION: A CASE STUDY IN CREDIT CARD FRAUD DETECTION |
|
Author(s):
|
Azamat Kibekbaev, Ekrem Duman |
|
ISBN:
|
978-989-8533-54-8 |
|
Editors:
|
Piet Kommers and Guo Chao Peng |
|
Year:
|
2016 |
|
Edition:
|
Single |
|
Keywords:
|
Fraud detection, Logistic regression, MBO, PSO, GA, ABC |
|
Type:
|
Full Paper |
|
First Page:
|
148 |
|
Last Page:
|
154 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
The amount of online transactions are increasing considerably with the development of modern technology in the finance industry, government, corporate sectors, and for ordinary consumers. Thus, forcing financial institutions to continuously improve their fraud detection systems is inevitable to minimize their losses. In recent years, there has been research done on many machine learning and data mining techniques for credit card fraud prevention and detection. However, most studies used some sort of misclassification measure to evaluate different solutions in terms of probability, and do not take into account the profitability or costliness of detecting a fraudulent transaction. The key contribution in our study is to focus on the profit maximization in the model building step. Proposed logistic regression algorithm in this study works based on profit maximization instead of minimizing the error of prediction. In addition, literature studies have shown that the maximum likelihood estimator which works as a gradient based algorithm, usually gets trapped in local optima and swarm-based (metaheuristic) algorithms are more successful in this respect. In this study, we train our profit maximization LR using the Migrating Birds Optimization, Particle Swarm Optimization, Genetic Algorithm and Artificial Bee Colony. |
|
|
|
|
|
|
