Microsoft Dynamics CRM Prediction with Azure Machine Learning

Machine learning is a type of artificial intelligence that provides computers
with the ability to learn without being explicitly programmed.Machine learning focuses on the development of computer programs that can teach themselves to grow and change when exposed to new data.

Some Machine Learning Concepts:

Supervised Learning

Supervised learning is a type of machine learning algorithm that uses a known dataset (called the training dataset) to make predictions. The training dataset includes input data and response values.

Unsupervised Learning

Unsupervised learning is a type of machine learning algorithm used to draw inferences from datasets consisting of input data without labeled responses.


This is a type of prediction used to predict Continuous Values. For example when we want to predict that how many sales will be happened in a year.


This is a type of prediction used to predict Discrete Values. For example When we want to predict if a person is a potential buyer or not.

Microsoft Azure Machine Learning

Microsoft Azure Machine Learning (ML) is a service that a developer can use to build predictive analytic models (using training data sets from a variety of data sources) and then easily deploy those models for consumption as cloud web services. Microsoft Azure ML provides different algorithms to process data that predict future values.

Dynamics CRM With Azure Machine Learning

Microsoft Azure Machine Learning can be used along with Dynamics CRM to predict data like future sales and outcome the opportunities etc.

In Dynamics CRM, right now there is no out of the box functionality to connect CRM to Azure Machine Learning. Microsoft announced to give this kind of functionality in November 2016. But as of now, we can use Web service from Workflow in Dynamics CRM to send data to Azure Machine Learning.

We can take an example like we have to determine if an opportunity will be won or lost, for that the first step in Azure Machine Learning is to make a train model using past data as input. To make a train model to predict the outcome of the opportunity we can extract opportunity data from CRM in CSV file and upload it into Azure Machine Learning Dataset and apply different algorithms like Decision Tree that are already available in azure machine learning.

With the trained model, we can bind it to a web service and that web service can be called from CRM through Workflow to predict whether the opportunity will be won or lost.

Leave a Reply