Machine learning is a technique of data science that helps apps, devices, and computers become smarter by learning from existing data in order to forecast future behaviors, outcomes, and trends.

Azure Machine Learning (AML) is a cloud predictive analytics service, which makes it easy to create and deploy predictive models as analytics solutions. AML uses algorithms to analyze historical/current data to identify patterns and to forecast future events.

Currently, there are predictive/cognitive capabilities available out of box in Dynamics 365 for Finance and Operations, Enterprise edition (AX), which use a combination of the Retail module, AML, and Cortana. In order to enable these capabilities, one can follow these steps:

1. One has to turn on Enable Recommendations in Machine learning | Retail parameters.
2. With this turned on, while making Point of Sale (POS) transactions, the user punching in sales will get recommendations of similar products bought together.
3. This recommendation setting on POS needs to be configured in a screen layout designer by using recommendation control in the Transactions screen.

AML benefits the forecasting process a lot with industry-proven algorithms that aid human decisions. 

Microsoft has a lot of tools, cloud services, and APIs on Azure, which can be used along with Dynamics 365 for highly complex needs in analytics.

Some of the key tools are as follows:

• Azure Data Factory:

  • Cloud service for processing structured and unstructured data from almost any source

  • You can understand it in terms similar to SSIS for managing all your data on the premises and cloud

• Azure Data Lake:

  • Azure Storage with almost infinite space to handle streaming data (low latency, high volume, and short updates)

  • It is geo-distributed, is data-locality aware, and it allows individual files to be sized at petabyte scale

  • An enterprise-wide repository of every type of data collected in a single place

• Azure SQL data warehouse:

  • It is a cloud-based, scale-out database capable of processing massive volumes of data, both relational and non-relational

  • Leverages the Massively Parallel Processing (MPP) architecture for all kinds of enterprise workload

• HDInsight:

  • It's a fully managed Hadoop cluster service that supports a wide range of analytic engines, including Spark, Storm, and HBase

  • It uses the Hortonworks Data Platform (HDP) distribution to manage, analyze, and report big data, providing a highly available and reliable environment for running Hadoop components

• Cognitive services:

  • Microsoft Cognitive Services APIs are a suite of several general-purpose machine learning APIs that are made available in Microsoft Azure and can be used for any number of applications

  • These APIs simplify the whole process by abstracting away the complex machine learning models and the operationalization aspects so that the users can focus on real business problems

We all have a journey to make and so does the decision making process, which starts with data, then information, and then actions:

The preceding image shows how data is converted into intelligence and action which is at the core principle in Cortana Intelligence Suite and Azure tools using AML. At the heart of any decision making process is the ability to see data representation to intelligence and also be able to act on the recommendations.

Together these tools/services helps in delivering advanced analytics with actionable intelligence and predictive/cognitive capabilities.