From the course: Power BI: Integrating AI

Unlock this course with a free trial

Join today to access over 24,800 courses taught by industry experts.

Leveraging anomaly detection

Leveraging anomaly detection - Power BI Tutorial

From the course: Power BI: Integrating AI

Start my 1-month free trial Buy for my team

Leveraging anomaly detection

“

- [Instructor] While outliers determine how far away from the rest of the data that a data point lies, anomaly detection measures how far away that data is from where we expect to be. Anomaly detection algorithms are unsupervised machine learning models. Power BI's built-in anomaly detection algorithm uses a density-based clustering model to help us find outliers. We can run an anomaly detection algorithm directly on an existing line chart to automatically find anomalies in the data, which displays our average temperature by day. We can add the anomalies through the Analytics pane, where we'll then turn on the anomalies functionality. Our algorithm runs behind the scenes in Power BI, so we don't need to know how it runs, but we do need to understand what these outcomes mean and any next steps we can take from there. There are only two outcome labels to this algorithm, either it's in the range of normal data or outside it. And when the data point is outside of it, then it's an anomaly.…

Contents