DBNex: Deep Belief Network and Explainable AI based Financial Fraud Detection

Abhimanyu Bhowmik; Madhushree Sannigrahi; Deepraj Chowdhury; Ashutosh Dhar Dwivedi; Raghava Rao Mukkamala

doi:10.1109/BigData55660.2022.10020494

DBNex: Deep Belief Network and Explainable AI based Financial Fraud Detection

Abhimanyu Bhowmik, Madhushree Sannigrahi, Deepraj Chowdhury, Ashutosh Dhar Dwivedi, Raghava Rao Mukkamala

Department of Digitalization

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

Abstract

The majority of financial transactions are now conducted virtually around the world. The widespread use of credit cards and online transactions encourages fraudulent activity. Thus, one of the most demanding real-world challenges is fraud detection. Unbalanced datasets, in which there are a disproportionately high number of non-fraud samples compared to incidents of fraud, are one of the key obstacles to effective fraud detection. A further factor complicating the learning process for cutting-edge machine learning classifiers is how quickly fraud behaviour changes. Thus, in this study, we suggest an efficient fraud detection methodology. We propose a unique nonlinear embedded clustering to resolve imbalances in the dataset, followed by a Deep Belief Network for detecting fraudulent transactions. The proposed model achieved an accuracy of 94% with a 70:30 ratio of training-validation dataset

Original language	English
Title of host publication	Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022
Editors	Shusaku Tsumoto, Yukio Ohsawa, Lei Chen, Dirk Van den Poel, Xiaohua Hu, Yoichi Motomura, Takuya Takagi, Lingfei Wu, Ying Xie, Akihiro Abe, Vijay Raghavan
Number of pages	10
Place of Publication	Los Alamitos, CA
Publisher	IEEE
Publication date	2022
Pages	3033-3042
ISBN (Print)	9781665480468
ISBN (Electronic)	9781665480451
DOIs	https://doi.org/10.1109/BigData55660.2022.10020494
Publication status	Published - 2022
Event	IEEE International Conference on Big Data. IEEE BigData 2022 - Osaka International Convention Center (OICC), Osaka, Japan Duration: 17 Dec 2022 → 20 Dec 2022 Conference number: 10 https://bigdataieee.org/BigData2022/

Conference

Conference	IEEE International Conference on Big Data. IEEE BigData 2022
Number	10
Location	Osaka International Convention Center (OICC)
Country/Territory	Japan
City	Osaka
Period	17/12/2022 → 20/12/2022
Internet address	https://bigdataieee.org/BigData2022/

Keywords

Financial fraud detection
Deep belief network
UMAP
DBSCAN
CTGAN
Explainable AI

Access to Document

10.1109/BigData55660.2022.10020494Licence: Unspecified

Handle.net

Persistent link

Cite this

Bhowmik, A., Sannigrahi, M., Chowdhury, D., Dwivedi, A. D., & Mukkamala, R. R. (2022). DBNex: Deep Belief Network and Explainable AI based Financial Fraud Detection. In S. Tsumoto, Y. Ohsawa, L. Chen, D. V. D. Poel, X. Hu, Y. Motomura, T. Takagi, L. Wu, Y. Xie, A. Abe, & V. Raghavan (Eds.), Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 (pp. 3033-3042). IEEE. https://doi.org/10.1109/BigData55660.2022.10020494

Bhowmik, Abhimanyu ; Sannigrahi, Madhushree ; Chowdhury, Deepraj et al. / DBNex : Deep Belief Network and Explainable AI based Financial Fraud Detection. Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 . editor / Shusaku Tsumoto ; Yukio Ohsawa ; Lei Chen ; Dirk Van den Poel ; Xiaohua Hu ; Yoichi Motomura ; Takuya Takagi ; Lingfei Wu ; Ying Xie ; Akihiro Abe ; Vijay Raghavan. Los Alamitos, CA : IEEE, 2022. pp. 3033-3042

@inproceedings{36f861f9c6b84879924e99f923d86731,

title = "DBNex: Deep Belief Network and Explainable AI based Financial Fraud Detection",

abstract = "The majority of financial transactions are now conducted virtually around the world. The widespread use of credit cards and online transactions encourages fraudulent activity. Thus, one of the most demanding real-world challenges is fraud detection. Unbalanced datasets, in which there are a disproportionately high number of non-fraud samples compared to incidents of fraud, are one of the key obstacles to effective fraud detection. A further factor complicating the learning process for cutting-edge machine learning classifiers is how quickly fraud behaviour changes. Thus, in this study, we suggest an efficient fraud detection methodology. We propose a unique nonlinear embedded clustering to resolve imbalances in the dataset, followed by a Deep Belief Network for detecting fraudulent transactions. The proposed model achieved an accuracy of 94% with a 70:30 ratio of training-validation dataset",

keywords = "Financial fraud detection, Deep belief network, UMAP, DBSCAN, CTGAN, Explainable AI, Financial fraud detection, Deep belief network, UMAP, DBSCAN, CTGAN, Explainable AI",

author = "Abhimanyu Bhowmik and Madhushree Sannigrahi and Deepraj Chowdhury and Dwivedi, {Ashutosh Dhar} and Mukkamala, {Raghava Rao}",

year = "2022",

doi = "10.1109/BigData55660.2022.10020494",

language = "English",

isbn = "9781665480468",

pages = "3033--3042",

editor = "Shusaku Tsumoto and Yukio Ohsawa and Lei Chen and Poel, {Dirk Van den} and Xiaohua Hu and Yoichi Motomura and Takuya Takagi and Lingfei Wu and Ying Xie and Akihiro Abe and Vijay Raghavan",

booktitle = "Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022",

publisher = "IEEE",

address = "United States",

note = "IEEE International Conference on Big Data. IEEE BigData 2022, IEEE BigData 2022 ; Conference date: 17-12-2022 Through 20-12-2022",

url = "https://bigdataieee.org/BigData2022/",

}

Bhowmik, A, Sannigrahi, M, Chowdhury, D, Dwivedi, AD & Mukkamala, RR 2022, DBNex: Deep Belief Network and Explainable AI based Financial Fraud Detection. in S Tsumoto, Y Ohsawa, L Chen, DVD Poel, X Hu, Y Motomura, T Takagi, L Wu, Y Xie, A Abe & V Raghavan (eds), Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 . IEEE, Los Alamitos, CA, pp. 3033-3042, IEEE International Conference on Big Data. IEEE BigData 2022, Osaka, Japan, 17/12/2022. https://doi.org/10.1109/BigData55660.2022.10020494

DBNex: Deep Belief Network and Explainable AI based Financial Fraud Detection. / Bhowmik, Abhimanyu; Sannigrahi, Madhushree; Chowdhury, Deepraj et al.
Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 . ed. / Shusaku Tsumoto; Yukio Ohsawa; Lei Chen; Dirk Van den Poel; Xiaohua Hu; Yoichi Motomura; Takuya Takagi; Lingfei Wu; Ying Xie; Akihiro Abe; Vijay Raghavan. Los Alamitos, CA: IEEE, 2022. p. 3033-3042.

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

TY - GEN

T1 - DBNex

T2 - IEEE International Conference on Big Data. IEEE BigData 2022

AU - Bhowmik, Abhimanyu

AU - Sannigrahi, Madhushree

AU - Chowdhury, Deepraj

AU - Dwivedi, Ashutosh Dhar

AU - Mukkamala, Raghava Rao

N1 - Conference code: 10

PY - 2022

Y1 - 2022

N2 - The majority of financial transactions are now conducted virtually around the world. The widespread use of credit cards and online transactions encourages fraudulent activity. Thus, one of the most demanding real-world challenges is fraud detection. Unbalanced datasets, in which there are a disproportionately high number of non-fraud samples compared to incidents of fraud, are one of the key obstacles to effective fraud detection. A further factor complicating the learning process for cutting-edge machine learning classifiers is how quickly fraud behaviour changes. Thus, in this study, we suggest an efficient fraud detection methodology. We propose a unique nonlinear embedded clustering to resolve imbalances in the dataset, followed by a Deep Belief Network for detecting fraudulent transactions. The proposed model achieved an accuracy of 94% with a 70:30 ratio of training-validation dataset

AB - The majority of financial transactions are now conducted virtually around the world. The widespread use of credit cards and online transactions encourages fraudulent activity. Thus, one of the most demanding real-world challenges is fraud detection. Unbalanced datasets, in which there are a disproportionately high number of non-fraud samples compared to incidents of fraud, are one of the key obstacles to effective fraud detection. A further factor complicating the learning process for cutting-edge machine learning classifiers is how quickly fraud behaviour changes. Thus, in this study, we suggest an efficient fraud detection methodology. We propose a unique nonlinear embedded clustering to resolve imbalances in the dataset, followed by a Deep Belief Network for detecting fraudulent transactions. The proposed model achieved an accuracy of 94% with a 70:30 ratio of training-validation dataset

KW - Financial fraud detection

KW - Deep belief network

KW - UMAP

KW - DBSCAN

KW - CTGAN

KW - Explainable AI

KW - Financial fraud detection

KW - Deep belief network

KW - UMAP

KW - DBSCAN

KW - CTGAN

KW - Explainable AI

U2 - 10.1109/BigData55660.2022.10020494

DO - 10.1109/BigData55660.2022.10020494

M3 - Article in proceedings

SN - 9781665480468

SP - 3033

EP - 3042

BT - Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022

A2 - Tsumoto, Shusaku

A2 - Ohsawa, Yukio

A2 - Chen, Lei

A2 - Poel, Dirk Van den

A2 - Hu, Xiaohua

A2 - Motomura, Yoichi

A2 - Takagi, Takuya

A2 - Wu, Lingfei

A2 - Xie, Ying

A2 - Abe, Akihiro

A2 - Raghavan, Vijay

PB - IEEE

CY - Los Alamitos, CA

Y2 - 17 December 2022 through 20 December 2022

ER -

Bhowmik A, Sannigrahi M, Chowdhury D, Dwivedi AD, Mukkamala RR. DBNex: Deep Belief Network and Explainable AI based Financial Fraud Detection. In Tsumoto S, Ohsawa Y, Chen L, Poel DVD, Hu X, Motomura Y, Takagi T, Wu L, Xie Y, Abe A, Raghavan V, editors, Proceedings - 2022 IEEE International Conference on Big Data, Big Data 2022 . Los Alamitos, CA: IEEE. 2022. p. 3033-3042 doi: 10.1109/BigData55660.2022.10020494