Machine Learning

Machine Learning is a core part of Artificial Intelligence (AI). It builds algorithms that allow computers to learn how to perform tasks from data instead of requiring a programmer to write code for those tasks. Machine Learning does this by generalizing from examples and is a more cost-effective and faster approach when Big Data is involved. Mathematical analysis of Machine Learning algorithms and their performance is a well-defined branch of theoretical computer science often referred to as computational learning theory.
Machine Learning technology has existed for years, but its re-surging because of the reduced costs of computing and storage, which is the fundamental infrastructure requirement.

What you can do with Machine Learning

Data Mining

  • Anomaly detection: This technique is used for credit card fraud detection. Companies can detect which transactions are outside the usual purchasing patterns of the user.
  • Association rules: Supermarkets and eCommerce sites use this method to discover customer purchasing habits by identifying which products are brought together.
  • Predictions: Banks use this to determine credit worthiness and probability of default for potential loans. Other uses include trading (building predictive models of prices and market volatilities), portfolio management and risk management.

Text Analysis

Machine Learning is used to classify information from text such as emails, chats, documents and even tweets. This gives companies the ability to do:

  • Spam filtering: With Machine Learning, email programs classify an email as spam based on the content in the email.
  • Sentiment analysis: This method can be used to classify if the opinion expressed by the writer is positive, neutral or negative. Do you want to know what your customers are talking about your company on Facebook / Twitter?
  • Information extraction: The system is taught to extract a particular piece of information such as keywords, addresses, names etc.
    Image Processing
  • Image tagging: The Machine Learning algorithms automatically detect faces or specified objects in a photo based on the photos that you manually tag.
  • Optical Character Recognition: The algorithms learn to identify a certain image as a written character and transform a scanned text document into a digital file.
  • Self-driving cars: Machine Learning is at the heart of the driver less car. It helps the car learn what is a stop sign or if a car is approaching by looking at each frame taken by a video camera.

What are different use cases across the enterprises?


Sales and account managers can get alerts from the algorithms about specific customers or deals that are at risk. Machine Learning gives management actionable, real-time insights about their customers and vendors.


Marketing campaigns can be personalized with Machine Learning to meet the needs of prospective customers. Customers can be given special offers based on their previous buying patterns.

Human Resources

Predictive analysis is playing an important role in HR departments today. Machine Learning models are being deployed to identify and recruit employees and also to make existing employees work more efficiently. It can also be used to predict, which employees are at risk of leaving.


The existing financial systems show historical financial transactions. But applications using Machine Learning show future opportunities and how to get more profits out of existing systems.

Azure Machine Learning:

Azure Machine Learning Studio is a GUI-based integrated development environment for constructing and operationalizing Machine Learning workflow on Azure.
Let’s understand the workflow of Azure ML

Reference: Analyze/Model -> Consume.

The first, and probably most tedious step is to collect the data you need in order to train your model. We’ll talk more about this later, but the point is data is often unorganized, incomplete or even conflicting. Fortunately, Azure ML Studio has a large number of tools to help you with that. Once we get our data right in sense of magnitude and correctness, we need to select the proper algorithm for model training. There are both supervised and unsupervised algorithms available from the regression, classification, clustering and anomaly detection families. Finally, after you pick your algorithm you need to evaluate and test your model. Usually, you’ll split your collected data into training, validation and test sets which you will use to train and test your model, respectively. Again, Azure ML Studio gives you support for that, and we’ll see this in one of the coming blogs.

The final result is – you have your (hopefully) well trained model, which you can use to predict outputs based on inputs that were not in your original data set. And this is where Azure ML Studio really shines – with a couple of clicks you can add intelligence to your (mobile) apps, websites or provide insights in BI tools such as Power BI or Microsoft Excel. This is done by adding a web service which acts as an interface between your model and client apps – web service can be invoked with a single request-response model, or it can be batched.


Start Using Azure Machine Learning Studio:

The only thing you need in order to use Azure Machine Learning Studio is a Microsoft account. You get:

  • Free access for a 1 month or 200 hours.
  • 10 GB storage
  • R and Python scripts support
  • Predictive web services