Deep Learning for Time Series Data (O’Reilly AI Conference)

Anodot Chief Data Scientist Ira Cohen and Arun Kejariwal, who led an in-house anomaly detection system at Twitter, share a novel two-step approach to building more reliable prediction models with the integration of anomalies.

Their talk, presented at O’Reilly Artificial Intelligence Conference 2019, outlines the benefits of coupling correlation analysis – using deep learning techniques – with anomaly detection and details the potential challenges based on production data.

About

Ira Cohen is co-founder and chief data scientist at Anodot, where he’s 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 more than 12 years of industry experience.

Arun Kejariwal is an R&D leader and data enthusiast who has previously served in management roles at Twitter, Netflix, Yahoo! and Machine Zone. He has also authored numerous publications statistical and machine learning, time series analysis, data-driven mobile marketing, software development, and hardware design. He is a self-described advocate of open source.

The O’Reilly AI Conference is where cutting-edge science meets new business implementation. It’s a deep dive into emerging AI techniques and technologies with a focus on how to use it in real-world implementations. You’ll dissect case studies, delve into the latest research, learn how to implement AI in your projects, share emerging best practices in intelligence engineering and applications, uncover AI’s limitations and untapped opportunities and anticipate how AI will change the business landscape.