ARCHIVE

One of the problems with statistical outliers is that they can be difficult to detect within the context of time series data. In this post, we’ll discuss how we can tune automated detection systems so that they become integral when it comes to identifying outliers across thousands to billions of metrics.

How do we track and monitor the performance of machine learning algorithms? Simple - with machine learning algorithms.

From biased training sets to problems with input features to not understanding context (i.e., ‘dumb AI’), problems abound when it comes to correctly and accurately tracking and monitoring machine learning models.

Small and slow leaks sink ships - by analogy, slow and small leaks can also cause significant losses for any business if not detected and fixed early.

In the final part of the "Metrics At Scale" series, we look at normal and abnormal behavior similarities, getting a sparse or lower dimensional vector representation, and creating a pattern matching engine.

The increasingly agile, data-driven approach to development, parsing user data and releasing new versions regularly, has left many in data operations at a loss. So how do you identify unknown unknowns happening right under your nose?

Yes, "Star Wars:, the classic space opera full of mystical intrigue and epic power struggles. Yet, at the center of the movie, data plays a critical role.

Major takeaways from my recent appearance at Amazon’s NYC AWS Loft with Amazon CTO Dr. Werner Vogels, where we discussed the present and future of machine learning and how it will push the boundaries of what's possible.

Should data analysts and other "knowledge sector" employees feel threatened by AI? Here's what industry experts have to say on the subject.