Prelert, the first vendor to package data science into downloadable applications for everyday users, today announced it is presenting an academic paper, "Anomaly Detection in Application Performance Monitoring Data," at the 2014 International Conference on Machine Learning and Computing (ICMLC), being held January 10-12 at the Bond Place Hotel, Toronto, Canada. Prelert's Chief Technical Officer, Dr. Stephen Dodson, and R&D Director, Thomas Veasey, will be presenting their paper, which explains the benefits of using analytics and machine learning to solve the problems associated with accurate application performance monitoring.

Veasey and Dodson's paper explains the significant impact performance issues and outages can have on business due to the inadequacy of traditional monitoring methods. The complexity of underlying systems, the volume and variety of performance metrics collected and the desire to correlate unusual application logging have made it harder than ever to find problems and anomalous behavior before they impact business. The argument of the paper is that the problem of monitoring effectively is well suited to analysis with a statistical model of the system state, and that Bayesian methods are particularly well suited to the formulation of the model. The results of applying this analytical model to data are shown to effectively pre-empt and diagnose system issues far faster than traditional methods when operationalized with machine learning.

"We're excited to engage with the academic community to share our technology and discuss future research directions," Dodson stated. "Our products involve packaging state of the art data science solutions in a downloadable format, and so it is important we contribute to and learn from academic communities to make this knowledge available to a wider audience."

For more information on Prelert's predictive analytics machine learning approach to anomaly detection visit http://www.prelert.com.

About Prelert

Mining answers from the volume of data available today to drive business decisions requires advanced analytics approaches that, until now, have required the expertise of data scientists. Prelert is the first vendor to provide this data science packaged to provide a time to value in minutes and enable IT and business professionals to make better decisions. Prelert: Data science for everyday decisions. For more information, visit www.prelert.com.

About ICMLC

The International Conference of Machine Learning and Computing (www.icmlc.org) is organized by the International Association of Computer Science and Information Technology (www.IACSIT.org). The mission of IACSIT is to foster and conduct collaborative interdisciplinary research in state-of-the-art methodologies and technologies within its areas of expertise. All papers accepted to ICMLC will be published in the volume of International Journal of Machine Learning and Computing (IJMLC), and will be included in the Engineering & Technology Digital Library, Google Scholar, Crossref, ProQuest, Electronic Journals Library, DOAJ and EI (INSPEC, IET).

Prelert
Heather DelCarpini, 508-319-5300
hdelcarpini@prelert.com