What is Machine Learning?

machine-learningMachine Learning is a fascinating era. It is when Computer Science joins forces with the Statistical Science and magical things popup. Why is that? Because by applying knowledge from both fields you are able to analyze a large amount of information, detect patterns, predict future outcomes and extract knowledge.

If I am to give a very simple and non-technical explanation of what Machine Learning is, I would say that it is when we train a computer to identify patterns, predict outcomes, identify common groups or relations between observations etc. For example you are able to predict the outcome of a particular variable given other parameters (For example predict the salary of an employee given his years of experience in a field, his age, his degrees and his area of expertise. This technique is known as Regression Analysis), classify particular records to specific categories (For example classify a document to particular Topics/Categories based on its words and phrases. This technique is known as Document Classification) or detect clusters of records that have the same characteristics (For example group the customers of a company based on their buying habits. This technique is known as Cluster Analysis).

Most computer programmers don’t realize the power that they have in their hands. Due to their background and knowledge they are able to process and store massive amount of information. They can write programs to extract information from the web, store them in a database and analyze them. If one analyzes these data properly, he can get very interesting results, acquire knowledge, build innovative applications and services or automate boring and time consuming tasks.

This is not science fiction! Machine Learning is in your everyday life! When you purchase something on Amazon, you get proposals based on your previous purchases. When you use Google and you are logged in with an account, Google tries to serve results that are more likely to be useful to you based on your browsing history. When you visit IMDB to look for a movie, they build a profile based on your clicks and they try proposing films that you will probably enjoy. When you use Facebook, they serve to you advertisements closely related to the things you like. Finally when you use your email service and the “anti-spam” filter blocks a particular email, this is machine learning classifying the message as junk.

Machine Learning is in your everyday life (even you like it or not) because it allows companies to use the massive amount of information that they have in order to detect automatically what their customers want and offer to them more targeted services.

Personally I have some experience in Machine Learning due to my involvement in WebSEOAnalytics.com and my Thesis project for my MSc in Statistics. Within the next blog posts I plan to share publicly an adapted version of my Thesis project in which I studied the topic of Sentiment Analysis. Sentiment Analysis is when you try to classify a document as either positive or negative (in other cases predict Subjectivity or Emotional states) based on its words or phrases. It is regularly used by Marketing Agencies and large corporations in order to detect what is the opinion of their clients when they publish posts on Social Media such as Twitter, Facebook, Forums or Blogs.

Sounds interesting? Stay tuned!

Did you like the article? Please take a minute to share it on Twitter. :)


My name is Vasilis Vryniotis. I’m a Software Engineer, Statistics & Machine Learning enthusiast, co-founder of WebSEOAnalytics.com, with experience in designing large scale web applications and knowledge in the areas of Online Marketing & SEO. Learn more

Latest Comments
  1. ANOOP

    Found this post very useful. I am also doing research in Machine Learning and AI related things. Great website to know about Machine Learning

Leave a Reply

Your email address will not be published. Required fields are marked *

− 2 = six

You may use these HTML tags and attributes: <a href="" title="" rel=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>