In this talk we shall shares a novel two-step approach for building more reliable prediction models by integrating anomalies in them. The first step uses anomaly detection algorithms to discover anomalies in a time series in the training data. In the second, multiple prediction models, including time series models and deep networks, are trained, enriching the training data with the information about the anomalies discovered in the first step.
Anomaly detection for individual time series is a necessary but insufficient step, due to the fact that anomaly detection over a set of live data streams may result in anomaly fatigue, thereby limiting effective decision making. One way to address the above is to carry out anomaly detection in a multidimensional space. However, this is typically very expensive computationally and hence not suitable for live data streams. Another approach is to carry out anomaly detection on individual data streams and then leverage correlation analysis to minimize false positives, which in turn helps in surfacing actionable insights faster.
To this end, we shall walk the audience through how to marry correlation analysis with anomaly detection, discusses how the topics are intertwined, and details the challenges you may encounter based on production data. We shall also showcase how deep learning can be leveraged to learn nonlinear correlation, which in turn can be used to further contain the false positive rate of an anomaly detection system.
Until recently, Arun Kejariwal was a statistical learning principal at Machine Zone (MZ), where he led a team of top-tier researchers and worked on research and development of novel techniques for install and click fraud detection and assessing the efficacy of TV campaigns and optimization of marketing campaigns. In addition, his team built novel methods for bot detection, intrusion detection, and real-time anomaly detection. Previously, Arun worked at Twitter, where he developed and open-sourced techniques for anomaly detection and breakout detection. His research includes the development of practical and statistically rigorous techniques and methodologies to deliver high-performance, availability, and scalability in large-scale distributed clusters. Some of the techniques he helped develop have been presented at international conferences and published in peer-reviewed journals.
Ira Cohen is a cofounder and chief data scientist at Anodot, where he is responsible for developing and inventing the company’s real-time multivariate anomaly detection algorithms that work with millions of time series signals. He holds a PhD in machine learning from the University of Illinois at Urbana-Champaign and has over 12 years of industry experience.
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
©2019, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org