Email this article A survey on detecting financial fraud with anomaly feature detection
Abstract
Trading/transaction arrange uncovers the cooperation among substances and therefore abnormality identification on exchanging systems can uncover the elements associated with the fraud movement; while highlights of elements are the portrayal of elements and irregularity location on highlights can reflect subtleties of the fraud exercises. In this way, system and highlights give integral data to fraud discovery, which can possibly improve fraud identification execution. Be that as it may, most of existing strategies center on systems or highlights data independently, which doesn't use both data. In this, we propose a novel fraud recognition structure, CoDetect, which can use both system data and highlight data for money related fraud location. What's more, CoDetect can all the while distinguishing money related fraud exercises and the element designs related with the fraud exercises.
References
C. Sullivan and E. Smith. ``Trade-Based Money Laundering: Risks andRegulatory Responses,'' Social Sci. Electron. Publishing, 2012, p. 6.
United Press International. (May 2009). Trade-Based MoneyLaundering Flourishing.[Online].Available:http://www.upi.com/TopNews/2009/05/11/Trade-based-money-laundering-_ourishing/UPI- 17331242061466
L. Akoglu, M. McGlohon, and C. Faloutsos, ``OddBall: Spotting anomaliesin weighted graphs,'' in Proc. Pacic-Asia Conf. Knowl. Discovery DataMining, 2010, pp. 410_421.
V. Chandola, A. Banerjee, and V. Kumar, ``Anomaly detection: A survey,''ACMComput. Surv., vol. 41, no. 3, 2009, Art. no. 15.
W. Eberle and L. Holder, ``Mining for structural anomalies in graph-baseddata,'' in Proc. DMin, 2007, pp. 376_389.
C. C. Noble and D. J. Cook, ``Graph-based anomaly detection,'' in Proc.9th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2003,pp. 631_636.
H. Tong and C.-Y. Lin, ``Non-negative residual matrix factorization withapplication to graph anomaly detection,'' in Proc. SIAM Int. Conf. DataMining, 2011, pp. 1_11.
S.Wang, J. Tang, and H. Liu, ``Embedded unsupervised feature selection,''in Proc. 29th AAAI Conf. Artif. Intell., 2015, pp. 470_476.
Z. Lin, M. Chen, and Y. Ma. (2010). ``The Augmented lagrange multipliermethod for exact recovery of corrupted low-rank matrices.'' [Online].Available: https://arxiv.org/abs/1009.5055.
J. Sun, H. Qu, D. Chakrabarti, and C. Faloutsos, ``Neighborhoodformationand anomaly detection in bipartite graphs,'' in Proc. 15th IEEE Int. Conf.Data Mining, Nov. 2005, p. 8.
A. Patcha and J.-M. Park, ``An overview of anomaly detection techniques:Existing solutions and latest technological trends,'' Comput. Netw., vol. 51,no. 12, pp. 3448_3470, Aug. 2007.
W. Li, V. Mahadevan, and N. Vasconcelos, ``Anomaly detection andlocalization in crowded scenes,'' IEEE Trans. Pattern Anal. Mach. Intell.,vol. 36, no. 1, p. 18_32, Jan. 2014.
K. Henderson et al., ``It's who you know: Graph mining using recursivestructural features,'' in Proc. 17th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2011, pp. 663_671.
F. Keller, E. Müller, and K. Bohm, ``HiCS: High contrast subspaces fordensity-based outlier ranking,'' in Proc. ICDE, Apr. 2012, pp. 1037_1048.
D. Koutra, E. Papalexakis, and C. Faloutsos, ``Tensorsplat: Spotting latentanomalies in time,'' in Proc. PCI, Oct. 2012, pp. 144_149.
Refbacks
- There are currently no refbacks.
Copyright © 2013, All rights reserved.| ijseat.com
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.