An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set

Sylvester Manlangit, Sami Azam, Bharanidharan Shanmugam, Krishnan Kannoorpatti, Mirjam Jonkman, Arasu Balasubramaniam

    Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

    Abstract

    Credit card fraudulent transactions are causing businesses and banks to lose time and money. Detecting fraudulent transactions before a transaction is finalized will help businesses and banks to save resources. This research aims to compare the fraud detection accuracy of different sampling techniques and classification algorithms. An efficient method of detecting fraud using machine learning is proposed. Anonymized data set from Kaggle was used for detecting fraudulent transactions. Each transaction has been labeled as either a fraudulent transaction or not. The severe imbalance between fraud and non-fraudulent data caused the algorithms to under-perform. This was addressed with the application of sampling techniques. The combination of undersampling and SMOTE raised the recall accuracy of the classification algorithm. k-NN algorithm showed the highest recall accuracy compared to the other algorithms.

    LanguageEnglish
    Title of host publicationIntelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017
    EditorsAjith Abraham, Pranab Muhuri, Azah Muda, Niketa Gandhi
    PublisherSpringer-Verlag London Ltd.
    Pages418-429
    Number of pages12
    ISBN (Electronic)9783319763484
    ISBN (Print)9783319763477
    DOIs
    StatePublished - 1 Jan 2018
    Event17th International Conference on Intelligent Systems Design and Applications, ISDA 2017 - Delhi, India
    Duration: 14 Dec 201716 Dec 2017

    Publication series

    NameAdvances in Intelligent Systems and Computing
    Volume736
    ISSN (Print)2194-5357

    Conference

    Conference17th International Conference on Intelligent Systems Design and Applications, ISDA 2017
    CountryIndia
    CityDelhi
    Period14/12/1716/12/17

    Fingerprint

    Sampling
    Learning systems
    Industry

    Cite this

    Manlangit, S., Azam, S., Shanmugam, B., Kannoorpatti, K., Jonkman, M., & Balasubramaniam, A. (2018). An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set. In A. Abraham, P. Muhuri, A. Muda, & N. Gandhi (Eds.), Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017 (pp. 418-429). (Advances in Intelligent Systems and Computing; Vol. 736). Springer-Verlag London Ltd.. DOI: 10.1007/978-3-319-76348-4_41
    Manlangit, Sylvester ; Azam, Sami ; Shanmugam, Bharanidharan ; Kannoorpatti, Krishnan ; Jonkman, Mirjam ; Balasubramaniam, Arasu. / An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set. Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017. editor / Ajith Abraham ; Pranab Muhuri ; Azah Muda ; Niketa Gandhi. Springer-Verlag London Ltd., 2018. pp. 418-429 (Advances in Intelligent Systems and Computing).
    @inproceedings{5977fc2c7dff45b488afa4ed5bbcf514,
    title = "An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set",
    abstract = "Credit card fraudulent transactions are causing businesses and banks to lose time and money. Detecting fraudulent transactions before a transaction is finalized will help businesses and banks to save resources. This research aims to compare the fraud detection accuracy of different sampling techniques and classification algorithms. An efficient method of detecting fraud using machine learning is proposed. Anonymized data set from Kaggle was used for detecting fraudulent transactions. Each transaction has been labeled as either a fraudulent transaction or not. The severe imbalance between fraud and non-fraudulent data caused the algorithms to under-perform. This was addressed with the application of sampling techniques. The combination of undersampling and SMOTE raised the recall accuracy of the classification algorithm. k-NN algorithm showed the highest recall accuracy compared to the other algorithms.",
    keywords = "Anonymized data, Credit card, Fraud detection",
    author = "Sylvester Manlangit and Sami Azam and Bharanidharan Shanmugam and Krishnan Kannoorpatti and Mirjam Jonkman and Arasu Balasubramaniam",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.1007/978-3-319-76348-4_41",
    language = "English",
    isbn = "9783319763477",
    series = "Advances in Intelligent Systems and Computing",
    publisher = "Springer-Verlag London Ltd.",
    pages = "418--429",
    editor = "Ajith Abraham and Pranab Muhuri and Azah Muda and Niketa Gandhi",
    booktitle = "Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017",
    address = "Germany",

    }

    Manlangit, S, Azam, S, Shanmugam, B, Kannoorpatti, K, Jonkman, M & Balasubramaniam, A 2018, An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set. in A Abraham, P Muhuri, A Muda & N Gandhi (eds), Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017. Advances in Intelligent Systems and Computing, vol. 736, Springer-Verlag London Ltd., pp. 418-429, 17th International Conference on Intelligent Systems Design and Applications, ISDA 2017, Delhi, India, 14/12/17. DOI: 10.1007/978-3-319-76348-4_41

    An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set. / Manlangit, Sylvester; Azam, Sami; Shanmugam, Bharanidharan; Kannoorpatti, Krishnan; Jonkman, Mirjam; Balasubramaniam, Arasu.

    Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017. ed. / Ajith Abraham; Pranab Muhuri; Azah Muda; Niketa Gandhi. Springer-Verlag London Ltd., 2018. p. 418-429 (Advances in Intelligent Systems and Computing; Vol. 736).

    Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

    TY - GEN

    T1 - An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set

    AU - Manlangit,Sylvester

    AU - Azam,Sami

    AU - Shanmugam,Bharanidharan

    AU - Kannoorpatti,Krishnan

    AU - Jonkman,Mirjam

    AU - Balasubramaniam,Arasu

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - Credit card fraudulent transactions are causing businesses and banks to lose time and money. Detecting fraudulent transactions before a transaction is finalized will help businesses and banks to save resources. This research aims to compare the fraud detection accuracy of different sampling techniques and classification algorithms. An efficient method of detecting fraud using machine learning is proposed. Anonymized data set from Kaggle was used for detecting fraudulent transactions. Each transaction has been labeled as either a fraudulent transaction or not. The severe imbalance between fraud and non-fraudulent data caused the algorithms to under-perform. This was addressed with the application of sampling techniques. The combination of undersampling and SMOTE raised the recall accuracy of the classification algorithm. k-NN algorithm showed the highest recall accuracy compared to the other algorithms.

    AB - Credit card fraudulent transactions are causing businesses and banks to lose time and money. Detecting fraudulent transactions before a transaction is finalized will help businesses and banks to save resources. This research aims to compare the fraud detection accuracy of different sampling techniques and classification algorithms. An efficient method of detecting fraud using machine learning is proposed. Anonymized data set from Kaggle was used for detecting fraudulent transactions. Each transaction has been labeled as either a fraudulent transaction or not. The severe imbalance between fraud and non-fraudulent data caused the algorithms to under-perform. This was addressed with the application of sampling techniques. The combination of undersampling and SMOTE raised the recall accuracy of the classification algorithm. k-NN algorithm showed the highest recall accuracy compared to the other algorithms.

    KW - Anonymized data

    KW - Credit card

    KW - Fraud detection

    UR - http://www.scopus.com/inward/record.url?scp=85044475668&partnerID=8YFLogxK

    U2 - 10.1007/978-3-319-76348-4_41

    DO - 10.1007/978-3-319-76348-4_41

    M3 - Conference Paper published in Proceedings

    SN - 9783319763477

    T3 - Advances in Intelligent Systems and Computing

    SP - 418

    EP - 429

    BT - Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017

    PB - Springer-Verlag London Ltd.

    ER -

    Manlangit S, Azam S, Shanmugam B, Kannoorpatti K, Jonkman M, Balasubramaniam A. An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set. In Abraham A, Muhuri P, Muda A, Gandhi N, editors, Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017. Springer-Verlag London Ltd.2018. p. 418-429. (Advances in Intelligent Systems and Computing). Available from, DOI: 10.1007/978-3-319-76348-4_41