• Corpus ID: 5611981

Meta Learning Algorithms for Credit Card Fraud Detection 1

  title={Meta Learning Algorithms for Credit Card Fraud Detection 1},
  author={S. Sen and Sujata Dash},
Due to the rapid advancement of electronic commerce technology, there is a great and dramatic increase in credit card transactions. As credit card becomes the most popular mode of payment for both online as well as regular purchase, cases of fraud associated with it are also rising; to detect credit card frauds in electronic transactions becomes the focus of risk of control of banks. The proposed work in this paper is the combination of five supervised machine learning algorithms… 

Figures and Tables from this paper

Credit Card Fraud Detection Using Machine Learning As Data Mining Technique

The combination of machine learning and data mining techniques were able to identify the genuine and non-genuine transactions by learning the patterns of the data and achieved more than 95.0% accuracy compared to results attained before preprocessing the dataset.

A Comparative Study and Performance Analysis of ATM Card Fraud Detection Techniques

This study aims to review alternative techniques that have been used in fraud detection and compare and analyze these techniques that are already used in ATM card fraud detection, to build a hybrid approach for developing some effective algorithms which can perform properly on fraud detection mechanism.

A survey - data mining frameworks in credit card processing

  • Pornwatthana WongchinsriWerasak Kuratach
  • Computer Science
    2016 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)
  • 2016
A systematic analysis and a comprehensive review of data mining techniques and their applications in the credit card process which divides into 4 main activities into research works which were published between 2007 and the first quarter of 2015 inclusively.

Financial Frauds: Data Mining based Detection – A Comprehensive Survey

The present survey analyses almost all published research work in the field of financial fraud detection for the period of 7 years starting from 2009 to help researchers in identifying the suitable variables and data mining techniques by providing the landscape of research platforms for detection of financial Fraud.

A semantic rule based digital fraud detection

This work proposes an ontology-based financial fraud detection and deterrence model that uses an Intimation Rule Based (IRB) alert generation algorithm and uses a richer domain knowledge base and rule-based reasoning.

Number 10

Qualitative/quantitative measurement of software using cluster analysis is discussed, including all the three associated in the list of seven factors with software reliability performance.



Neural data mining for credit card fraud detection

  • Tao GuoGuiyang Li
  • Computer Science
    2008 International Conference on Machine Learning and Cybernetics
  • 2008
This paper shows how confidence value, neural network algorithm and ROC can be combined successfully to perform credit card fraud detection.

Credit card fraud detection with a neural-network

  • Sushmito GhoshD. Reilly
  • Computer Science
    1994 Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences
  • 1994
Using data from a credit card issuer, a neural network based fraud detection system was trained on a large sample of labelled credit card account transactions and tested on a holdout data set that

Distributed data mining in credit card fraud detection

The proposed methods of combining multiple learned fraud detectors under a "cost model" are general and demonstrably useful; the empirical results demonstrate that they can significantly reduce loss due to fraud through distributed data mining of fraud models.

A Neural Classifier with Fraud Density Map for Effective Credit Card Fraud Detection

To reduce mis-detections, the fraud density of real transaction data is taken as a confidence value and generated as a weighted fraud score in the proposed scheme to improve the detection efficiency.

Credit Card Fraud Detection Using Meta-Learning: Issues and Initial Results 1

It is argued that, for the fraud detection domain, fraud catching rate and false alarm rate are better metrics than the overall accuracy when evaluating the learned fraud classifiers, and that given a skewed distribution in the original data, artificially more balanced training data leads to better classifiers.

Minority report in fraud detection: classification of skewed data

This paper compares the new fraud detection method (meta-learning approach) against C4.5 trained using undersampling, oversamplings, and SMOTEing without partitioning, and shows that, given a fixed decision threshold and cost matrix, the partitioning and multiple algorithms approach achieves marginally higher cost savings than varying the entire training data set with different class distributions.

Parallel granular neural networks for fast credit card fraud detection

  • M. SyedaY. ZhangY. Pan
  • Computer Science
    2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291)
  • 2002
A parallel granular neural network (GNN) is developed to speed up data mining and knowledge discovery process for credit card fraud detection and gives fewer average training errors with larger amount of past training data.

CARDWATCH: a neural network based database mining system for credit card fraud detection

CardWATCH, a database mining system used for credit card fraud detection, is presented and test results obtained for synthetically generated credit card data and an autoassociate neural network model show very successful fraud detection rates.

A Comprehensive Survey of Data Mining-based Fraud Detection Research

Agent-Based Distributed Learning Applied to Fraud Detection

An AI-based approach that supports the cooperation among different institutions and consists of pattern-directed inference systems that use models of anomalous or errant transaction behaviors to forewarn of fraudulent practices is described.