From our previous article (How to Scale and Deal with Millions of Metrics), we looked at correlations in terms of name similarity, but there are other types of similarities that occur between metrics. Abnormal Behavior Similarities Metrics can be correlated by their abnormal behavior. When anomalies often appear at the same time in two metrics,…
What’s surprising to see today is how business operations struggle to get an integrated view of all business metrics. With greater volumes of data being collected, data analysts just can’t keep up with the pace. This state of affairs alone doesn’t hit as hard as the fact that many in data analytics have just come…
With businesses collecting millions of metrics, let’s look at how they can efficiently scale and deal with these amounts. As covered in the previous article (A Spike in Sales Is Not Always Good), analyzing millions of metrics for changes may result in alert storms, notifying users about EVERY change, not just the most significant ones.…
As Product Managers, you are responsible for the entire product. You can’t just assume that monitoring and alerts are being covered by someone else. In the first days of a release, all eyes are on the new product or latest feature. Just a few months later, when you introduce a brand new feature, the old…
Why could a spike itself not always be good news? Why is it so important to find the relationships between time series metrics at scale? Sunglass Orders Suddenly Spike Let’s start with an example from eCommerce. An eCommerce company is selling different products online. There is a sudden increase in the number of orders of…
One of Christopher Nolan’s earlier films, Memento, really captures the feeling of being a data analyst looking for insights while monitoring growing volumes of data. How is Lack of Memory like Monitoring Today’s Data? In Memento, the story is revealed (in reverse) about an insurance investigator that suffers from anterograde amnesia (an inability to form…
One of the essential lessons to be learned from Star Wars is that: If you are trying to establish and maintain a ruthless Galactic Empire, you can greatly benefit from better data aggregation and analysis. A prime landscape for exploring today’s big data issues can be found across the Star Wars universe. Yes, Star Wars,…
For business today, analyzing streaming data in real time, continuously generated from thousands of data sources, is not a simple process. Typically data records are sent simultaneously and in small sizes (on the order of bytes or kilobytes). Companies making real-time business decisions based on streaming data turn to a wide variety of sources such…
Machine Learning and the general perception of this field has come a long way since I finished my PhD in 2003. Back then, if I would tell people about my research on Machine Learning, there wasn’t a wide understanding, most people that I meant Learning by Machine, some kind of new approach to applying technology…
Product managers often A/B test their innovations, before releasing them for the standard user experience. Whether this is complete redesign of a UI layout or for a specific new login mechanism, various product developments undergo A/B testing before rollout. This way you can prove that the new experience is preferred over the old. But, have…
GDC was an incredible experience. It was immense, bright, and frenetic; exactly what you would want at a conference highlighting some of the most innovative technology in the gaming industry. Many of the vendors and booths were spectacular and warranted the long lines and anticipation. Wandering the maze of booths and exhibits, it was apparent…
We have a webinar coming up! Hear how Pandora is using anomaly detection and get some great insights from 451 research! I am so excited about the upcoming webinar, this Wednesday, at 9:00 a.m. PDT, “AI-Based Anomaly Detection for Proactive Business Monitoring.“ And guess what? We want you to attend. Here are 5 good reasons…