The purpose of Machine Learning model is to understand the given data and then make prediction without human intervention. Any machine learning model take the given data and fit the data as per the requirements. In supervised machine learning context, the data is given to the model with column names. These column names are also called as features or labels. Along with them, the target column will also be mentioned. It is clear to the model that what is to be predicted from the given features.

On the other hand the data is given to the model without any column names. Even the target column will not be there. In this case the model will look patterns in the data. These patterns may provide some information to the model. Thus the model will provide some useful information about the data even though it is not making any prediction. This type of learning is called as un-supervised machine learning.

In Unsupervised Machine Learning, the machine uses unlabeled data and learns on itself without any supervision. The machine tries to find a pattern in the unlabeled data and gives a response.

Supervised Machine Learning vs. Unsupervised Machine Learning

Supervised machine learning models take data with column names and target value to be predicted. That means in supervised machine learning we will consider independent variables(also called as input variables that is X) and target variable(also called as output variable that is y). By taking the value of X, the model will predict the value of y. The data is divided into training and testing data. The model understand the training data and check their learning accuracy using testing data.

On the other hand, the unsupervised machine learning models don’t have the data with labels and target columns. The model try to understand the given data by extracting features and patterns on their own. The model will not make any predictions but provide some information about the given data.

<Classification of Supervised and Unsupervised Models>