top of page

Data Scientist Program


Free Online Data Science Training for Complete Beginners.

No prior coding knowledge required!

Supervised vs. Unsupervised Learning: What's the Difference?

In this article you will find simple explanations for machine learning in general, supervised and unsupervised learning.

1. What is Machine Learning

Machine learning is a branch of artificial intelligence (AI) and computer science that focuses on using data and algorithms to mimic the way humans learn, gradually improving its accuracy.

2. Supervised Vs Unsupervised learning

Supervised and unsupervised learning represent the two key methods in which machines (algorithms) can automatically learn and improve from experience.

what is supervised learning?

We have supervised learning when a computer uses given labels as examples to take and sort sets of data and thereby predict future events.

in supervised learning, people teach or train the machine using labeled data. Labeled data means that it is already labeled with the correct answer.

  • There are two types of supervised learning algorithms:

Régression : is a supervised machine learning technique that is used to predict continuous values.

Classification : machine learning classification algorithms are at the heart of a large number of data mining problems and tasks.

In supervised learning we can find this list of algorithms:

  • Decision trees

  • K Nearest neighbors

  • Linear SVC (Support Vector Classifier)

  • Logistic regression

  • naive bayes

  • Neural networks

  • Linear regression

  • Support Vector Regression (SVR)

  • Regression trees (e.g. random forest)

  • Gradient increase

  • Fisher's linear discriminant.

what is unsupervised learning?

Unsupervised learning sorts things out without using predefined labels. Unsupervised machine learning algorithms operate without human guidance.

There are two two categories of algorithms in Unsupervised learning :

Clustering : The goal of clustering is to separate groups with similar characteristics and then assign them into clusters.

Association : Association is about discovering interesting relationships between variables in large databases. we have association rules that aim to find associations between data objects in large databases.

the main unsupervised machine learning algorithms and techniques are:

  • K-stands for clustering

  • K-NN (k nearest neighbors)

  • Dimensionality reduction

  • Neural Networks / Deep Learning

  • Principal component analysis

  • Decomposition of singular values

  • Independent component analysis

  • Distribution models

  • Hierarchical clustering

  • Mix models

Supervised Learning

​Unsupervised Learning


  • allows you to be very precise

  • You are able to determine the number of classes

  • The input data is well known

  • The results produced by the supervised method are more accurate

  • Less complexity

  • Happens in real time

  • It is often easier to get unlabeled data


  • can be a complex method

  • It does not take place in real time

  • You can't be very specific

  • less accuracy


Although we have highlighted the advantages and disadvantages of supervised and unsupervised learning, it is not very accurate to say that one of these methods has more advantages than the other.

Both methods of machine learning algorithms have a huge place in data mining and you need to know the difference between supervised and unsupervised learning.


Recent Posts

See All


bottom of page