Sponsored by

Description:

Anomaly detection is used widely to perform various tasks such as fraud detection in the financial industry, network breach for cyber-security, and enemy surveillance for the military. Data scientists apply various models to find anomalies, using a range of techniques from statistics to machine learning. However, the explosion of time series data generated by the Internet of Things (IoT) has made this task more challenging than ever. In the area of predictive maintenance, for example, data scientists struggle with hundreds of sensors that generate data every millisecond in order to find the unwanted noise that may lead to machine failure. Now, data scientists not only need to find the right algorithms to apply in these massive data sets, but they also need to find the right tools to handle big data.

Join us for a live webcast where you will learn how to:

1. Overcome common challenges in finding anomalies in time series data
2. Apply various statistical and machine learning algorithms in time series data
3. Differentiate event-based anomaly detection and pattern-based anomaly detection
4. Use tools that provide multi-genre analytics capability, such as Teradata Aster, to tackle anomaly detection

About Cheryl Wiebe, Practice Lead, Advanced Analytics – Teradata

Cheryl Wiebe is the Analytics of Things Practice Lead for the Advanced Analytics Center of Expertise within Teradata. The digitalization megatrend has been central to her work over the past 15 years, consulting with global 1000 clients who are embedding and operationalizing analytics at scale into industrial internet, smart cities, connected factory, smart grid, and other emerging IoT landscapes. She collaborates with business and advanced analytics professionals to accelerate their capabilities and professionalize their advanced analytics practices. Recent projects have focused on our clients who are initiating their Internet of Things journey in two areas: 1) how to align business strategy with analytics investments to get started on the road to being Competitors in Analytics of Things Competitors, and 2) how to build a robust data infrastructure to make sensor data and the many other related data types available at scale to allow Analytics of Things to be built into industrial analytic applications.

About Todd Morley, Chief Data Scientist, Early Warning Systems – Teradata

Todd Morley, is a senior data scientist in Teradata's Advanced Analytics COE, and the architect of VAP. His book Data Science Design Patterns, will be released soon by Addison Wesley. He has taught graduate data science and data architecture at UCCS and has written over a half-million lines of code.