The Impact of Deep Learning on Anomaly Detection
How deep learning will reshape the landscape of fraud detection, compliance and risk monitoring, and many other anomaly detection applications.
August 10, 2020 at 07:00 AM
6 minute read
Anomaly detection, or outlier detection, is the identification of data points, observations, or events that do not conform to expected patterns of a given group. Anomalies or outliers occur very infrequently but can signify a large and significant threat, such as cyber intrusion, financial fraud, compliance violation, and machinery malfunction, to businesses. Anomaly detection has traditionally relied on subject matter experts to curate and set business rules to trigger red flags in data. This traditional approach is inherently flawed because:
|- As the methodology is highly dependent on subject matter experts' knowledge and experience, the results can be subjective or biased.
- It entails a long and expensive development cycle to cultivate and refine the set of business rules.
- Oftentimes, business rules are not precise enough, difficult to manage overtime and may contradict one another.
Machine learning-based anomaly detection algorithms are a leap forward from the rule-based solution. However, conventional machine learning algorithms oftentimes fail to achieve a satisfactory performance level to end users due to several reasons.
|- First, as anomalies are rare and expensive to be investigated, many organizations have few or no historical labels on anomalies. The lack of historical data and sparsity in labels impede the use of supervised machine learning algorithms.
- Different anomaly detection algorithms rely on different assumptions and are domain specific. There is no one-size-fits-all anomaly detection algorithm.
- Customizing anomaly detection algorithms is non-trivial as it relies heavily on feature engineering. This is an increasing challenge with rapidly rising data velocity and variety in today's business world.
In recent years, deep learning-based anomaly detection solutions have gained great momentum and showed superior performance in various domains. In contrast to the conventional machine learning algorithms, a deep learning algorithm thrives in a high-dimensional data rich environment. It has the ability to explore feature interactions and execute feature engineering by itself. It is also highly flexible in adapting to different types of data, structured or unstructured, by using the appropriate neural network design. Popular deep learning architectures that can be used in an anomaly detection framework include:
Autoencoder: Autoencoders learn compact representations of complex datasets by encoding them through an unsupervised training process, in which high-dimensional multivariate datasets are represented in lower dimensions. For example, when an autoencoder is trained on a dataset consisting entirely of normal transactions, the autoencoder will learn very well how to encode a normal transaction to a compact representation and then decode the compact representation back to a transaction. The reconstruction error of this encode-decode process will be very low. However, when the autoencoder is faced with abnormal transactions, we expect higher reconstruction error and those transactions will be flagged as anomalies.
Generative Adversarial Network (GAN): GAN is a framework for the estimation of generative models via an adversarial process in which two models, a generator and a discriminator, are trained simultaneously. The idea being that two models (generator and discriminator) compete with each other during training such that the former tries to capture normal data distribution and generate data, while the latter distinguishes between real and generated data. A well-trained discriminator can then be used to detect anomalies.
This content has been archived. It is available through our partners, LexisNexis® and Bloomberg Law.
To view this content, please continue to their sites.
Not a Lexis Subscriber?
Subscribe Now
Not a Bloomberg Law Subscriber?
Subscribe Now
NOT FOR REPRINT
© 2024 ALM Global, LLC, All Rights Reserved. Request academic re-use from www.copyright.com. All other uses, submit a request to [email protected]. For more information visit Asset & Logo Licensing.
You Might Like
View AllTrending Stories
Who Got The Work
Michael G. Bongiorno, Andrew Scott Dulberg and Elizabeth E. Driscoll from Wilmer Cutler Pickering Hale and Dorr have stepped in to represent Symbotic Inc., an A.I.-enabled technology platform that focuses on increasing supply chain efficiency, and other defendants in a pending shareholder derivative lawsuit. The case, filed Oct. 2 in Massachusetts District Court by the Brown Law Firm on behalf of Stephen Austen, accuses certain officers and directors of misleading investors in regard to Symbotic's potential for margin growth by failing to disclose that the company was not equipped to timely deploy its systems or manage expenses through project delays. The case, assigned to U.S. District Judge Nathaniel M. Gorton, is 1:24-cv-12522, Austen v. Cohen et al.
Who Got The Work
Edmund Polubinski and Marie Killmond of Davis Polk & Wardwell have entered appearances for data platform software development company MongoDB and other defendants in a pending shareholder derivative lawsuit. The action, filed Oct. 7 in New York Southern District Court by the Brown Law Firm, accuses the company's directors and/or officers of falsely expressing confidence in the company’s restructuring of its sales incentive plan and downplaying the severity of decreases in its upfront commitments. The case is 1:24-cv-07594, Roy v. Ittycheria et al.
Who Got The Work
Amy O. Bruchs and Kurt F. Ellison of Michael Best & Friedrich have entered appearances for Epic Systems Corp. in a pending employment discrimination lawsuit. The suit was filed Sept. 7 in Wisconsin Western District Court by Levine Eisberner LLC and Siri & Glimstad on behalf of a project manager who claims that he was wrongfully terminated after applying for a religious exemption to the defendant's COVID-19 vaccine mandate. The case, assigned to U.S. Magistrate Judge Anita Marie Boor, is 3:24-cv-00630, Secker, Nathan v. Epic Systems Corporation.
Who Got The Work
David X. Sullivan, Thomas J. Finn and Gregory A. Hall from McCarter & English have entered appearances for Sunrun Installation Services in a pending civil rights lawsuit. The complaint was filed Sept. 4 in Connecticut District Court by attorney Robert M. Berke on behalf of former employee George Edward Steins, who was arrested and charged with employing an unregistered home improvement salesperson. The complaint alleges that had Sunrun informed the Connecticut Department of Consumer Protection that the plaintiff's employment had ended in 2017 and that he no longer held Sunrun's home improvement contractor license, he would not have been hit with charges, which were dismissed in May 2024. The case, assigned to U.S. District Judge Jeffrey A. Meyer, is 3:24-cv-01423, Steins v. Sunrun, Inc. et al.
Who Got The Work
Greenberg Traurig shareholder Joshua L. Raskin has entered an appearance for boohoo.com UK Ltd. in a pending patent infringement lawsuit. The suit, filed Sept. 3 in Texas Eastern District Court by Rozier Hardt McDonough on behalf of Alto Dynamics, asserts five patents related to an online shopping platform. The case, assigned to U.S. District Judge Rodney Gilstrap, is 2:24-cv-00719, Alto Dynamics, LLC v. boohoo.com UK Limited.
Featured Firms
Law Offices of Gary Martin Hays & Associates, P.C.
(470) 294-1674
Law Offices of Mark E. Salomone
(857) 444-6468
Smith & Hassler
(713) 739-1250