Data Science | Datadog

Rethinking UX for AI-driven Alerting

The introduction of advanced statistical methods is reshaping the UX of alerts

Auto-smooth noisy metrics to reveal trends

Datadog's new Auto Smoother function makes it simple to smooth out noisy metrics without losing sight of the ...

Robust Statistical Distances for Machine Learning

Designing powerful outlier and anomaly detection algorithms requires using the right tools. Discover how ...

Piecewise regression: when one line simply isn’t enough

A piecewise regression can model multiple trends in a single data set. Learn how Datadog automates piecewise ...

Introducing new scaled algorithms for improved outlier detection

Our new outlier detection algorithms take magnitude and dispersion into account for better alerting.

Visualizing trends with regression lines

When you care more about how a metric is trending over time and less about its exact value at every instant, ...

Outlier detection in Datadog: A look at the algorithms

Technical details behind the implementation of the DBSCAN and MAD algorithms for automated outlier detection ...

Get Started with Datadog