Azure Cognitive Services - Create Anomaly Detector

In this article, we’ll learn about creating the Anomaly Detector Service in Azure Cognitive Services which can be used for numerous projects that require Anomaly Detection service in Machine Learning and Data Science. This article is a part of the Azure Cognitive Services series and is a pre-requisite for  Azure Cognitive Services - Anomaly Detection Tutorial.

Azure Cognitive Services 

Azure Cognitive Services is one of the services offered by Microsoft Azure that enables a wide range of organizations to build cognitive intelligence for applications with client library SDKs and REST APIs. Azure Cognitive Services allows developers to integrate cognitive features into applications with no prior knowledge of Machine Learning, Data Science, and Artificial Intelligence skillset. From Computer Vision to Natural Language Processing and Conversational AI, Azure Cognitive Services provides the support for a diverse prospect of applications.

Anomaly Detection

Anomaly detection helps in finding out anomaly ie. Usually detection of errors and unusual activities. It is basically analysis to find out outliers which are these observations or data points that deviate from the normal behavior of a particular dataset. Numerous use cases such as Credit Card Fraud Detection, Event Detection in Networks, Cyber Security Intrusion Identification can be performed with Anomaly Detection.

You can explore the other Azure Cognitive Services articles from the link below.

  1. Azure Cognitive Services – Create Text Analytics Service for Natural Language Processing 
  2. Azure Cognitive Services – Create Anomaly Detector 
  3. Azure Cognitive Services - Anomaly Detection Tutorial 
  4. Azure Cognitive Services - Sentiment Analysis Tutorial 

Now, let us learn to create the Anomaly Detector service under Cognitive Services in Azure.

Step 1

First of all, sign in to the Azure Portal. The home page will look similar to as below.

Step 2

Now, in the search bar, search for Anomaly Detector and select it.

Step 3

Now, we are taken to the Anomaly Detector Page.

Here, Click on Create.

Step 4

We are provided with the project details to be filled in.

Select your Subscription, Resource Group, and Instance Details. Fill in the name for the instance and choose the Pricing Tier. For now, it is fine to go with the Free F0 Tier which will provide 20K Transaction per month for free and supports 10 Calls per second. For any application which will have huge number of users calling more than 10 simultaneous calls, we would need a higher tier which will incur some charges.

Step 5

Now, Click on Review + Create.

The Validation takes place and with the Green Tick notification, we are now allowed to Create the service.

Step 6

The Initialization is in deployment now and we are notified in the notification bar.

Step 7

Here, on the Service page, we can see the update in the deployment progress.

Step 8

As the service is created, we are notified and thus are now enabled with the Go to Resource button. Click it.

Step 9

We can see the service ojash-anomaly has been created. We can see the various details in the Anomaly Detector Service page here from Status, Location, Subscription to Pricing Tier, Endpoint, and Key Access.

Step 10

Under the Keys and Endpoint of Resource Management, Click on Keys and Endpoint.

We are now given access to view the two Keys, Key 1 and Key 2. We can copy either of these keys from the copy button and use it to access our service that is key for the Azure Cognitive Services - Anomaly Detection Tutorial.

Thus, with this, we have now created the Anomaly Detector Service and is ready for any project which requires the Anomaly Detector functionality of Azure Cognitive Service.


Thus, in this article, we learned about Anomaly Detector and then went on a step-by-step process to create a Anomaly Detector Service in Azure. We can use this service for various applications of our need to perform Machine Learning and Data Science tasks.