Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism

Idan Achituve; Sarit Kraus; Jacob Goldberger

doi:10.1109/MLSP.2019.8918896

Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism

Idan Achituve, Sarit Kraus, Jacob Goldberger

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

18 Scopus citations

Abstract

Online banking activities are constantly growing and are likely to become even more common as digital banking platforms evolve. One side effect of this trend is the rise in attempted fraud. However, there is very little work in the literature on online banking fraud detection. We propose an attention based architecture for classifying online banking transactions as either fraudulent or genuine. The proposed method allows transparency to its decision by identifying the most important transactions in the sequence and the most informative features in each transaction. Experiments conducted on a large dataset of real online banking data demonstrate the effectiveness of the method in terms of both classification accuracy and interpretability of the results.

Original language	English
Title of host publication	2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019
Publisher	IEEE Computer Society
ISBN (Electronic)	9781728108247
DOIs	https://doi.org/10.1109/MLSP.2019.8918896
State	Published - Oct 2019
Event	29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019 - Pittsburgh, United States Duration: 13 Oct 2019 → 16 Oct 2019

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume	2019-October
ISSN (Print)	2161-0363
ISSN (Electronic)	2161-0371

Conference

Conference	29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019
Country/Territory	United States
City	Pittsburgh
Period	13/10/19 → 16/10/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Online banking
attention
deep learning
fraud detection
interpretability

Access to Document

10.1109/MLSP.2019.8918896

Cite this

Achituve, I., Kraus, S., & Goldberger, J. (2019). Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism. In 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019 Article 8918896 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2019-October). IEEE Computer Society. https://doi.org/10.1109/MLSP.2019.8918896

@inproceedings{3505e83f13c9423183f971fea81df5b5,

title = "Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism",

abstract = "Online banking activities are constantly growing and are likely to become even more common as digital banking platforms evolve. One side effect of this trend is the rise in attempted fraud. However, there is very little work in the literature on online banking fraud detection. We propose an attention based architecture for classifying online banking transactions as either fraudulent or genuine. The proposed method allows transparency to its decision by identifying the most important transactions in the sequence and the most informative features in each transaction. Experiments conducted on a large dataset of real online banking data demonstrate the effectiveness of the method in terms of both classification accuracy and interpretability of the results.",

keywords = "Online banking, attention, deep learning, fraud detection, interpretability",

author = "Idan Achituve and Sarit Kraus and Jacob Goldberger",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019 ; Conference date: 13-10-2019 Through 16-10-2019",

year = "2019",

month = oct,

doi = "10.1109/MLSP.2019.8918896",

language = "אנגלית",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

publisher = "IEEE Computer Society",

booktitle = "2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019",

address = "ארצות הברית",

}

Achituve, I, Kraus, S & Goldberger, J 2019, Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism. in 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019., 8918896, IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2019-October, IEEE Computer Society, 29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019, Pittsburgh, United States, 13/10/19. https://doi.org/10.1109/MLSP.2019.8918896

Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism. / Achituve, Idan; Kraus, Sarit ; Goldberger, Jacob.
2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019. IEEE Computer Society, 2019. 8918896 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2019-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism

AU - Achituve, Idan

AU - Kraus, Sarit

AU - Goldberger, Jacob

PY - 2019/10

Y1 - 2019/10

N2 - Online banking activities are constantly growing and are likely to become even more common as digital banking platforms evolve. One side effect of this trend is the rise in attempted fraud. However, there is very little work in the literature on online banking fraud detection. We propose an attention based architecture for classifying online banking transactions as either fraudulent or genuine. The proposed method allows transparency to its decision by identifying the most important transactions in the sequence and the most informative features in each transaction. Experiments conducted on a large dataset of real online banking data demonstrate the effectiveness of the method in terms of both classification accuracy and interpretability of the results.

AB - Online banking activities are constantly growing and are likely to become even more common as digital banking platforms evolve. One side effect of this trend is the rise in attempted fraud. However, there is very little work in the literature on online banking fraud detection. We propose an attention based architecture for classifying online banking transactions as either fraudulent or genuine. The proposed method allows transparency to its decision by identifying the most important transactions in the sequence and the most informative features in each transaction. Experiments conducted on a large dataset of real online banking data demonstrate the effectiveness of the method in terms of both classification accuracy and interpretability of the results.

KW - Online banking

KW - attention

KW - deep learning

KW - fraud detection

KW - interpretability

UR - http://www.scopus.com/inward/record.url?scp=85077723448&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2019.8918896

DO - 10.1109/MLSP.2019.8918896

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85077723448

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP 2019

PB - IEEE Computer Society

T2 - 29th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2019

Y2 - 13 October 2019 through 16 October 2019

ER -

Interpretable Online Banking Fraud Detection Based on Hierarchical Attention Mechanism

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this