Anomaly detection on streaming data using Azure Databricks

In our previous episodes of the AI Show, we've learned all about the Azure Anomaly detector, how to bring the service on premises, and some awesome tips and tricks for getting the service to work well for you. In this episode of the AI Show Qun Ying shows us how to build an end-to-end solution using the Anomaly Detector and Azure Databricks. This step by step demo detects numerical anomalies from streaming data coming through Azure Event Hubs.

Additional Information Links:

• Check out the detailed tutorial for the solution we've built in this episode
• Check out a simple demo
• Check out the overview of the API service
• Create your first Anomaly Detector resource on Azure
• Join Anomaly Detector Containers preview
• Join "Anomaly Detector Advisors" public community to connect with the product team and other members in the community

Re-Visit Your Favorite Part of the Video:

• [00:74] The business problem of the demo solution.
• [01:18] The architecture of the solution.
• [02:25] Solution prerequisites and resource setup.
• [06:11] Code walkthrough of sending tweets to Event Hubs.
• [07:08] Code walkthrough of reading tweets from Event Hubs.
• [09:25] Code walkthrough of data aggregation and storing to delta.
• [11:28] Code walkthrough of anomaly detection with Anomaly Detector.

The AI Show's Favorite Links:

• Don't miss new episodes, subscribe to the AI Show
• Create a Free account (Azure)
• Follow Seth on Twitter
• AI Blog
• Fast ML
• MIT News | AI
• Medium | Francesca Lazzeri
• Deep Learning vs. Machine Learning
• Follow Channel 9 On Twitter