Supervised Learning

Unsupervised Learning

Deals with known and labelled data

Deals with unknown and unlabeled data

Input variables and output variables are specified

Only input data are specified

The ultimate goal is to determine the function so well that when new input dataset is given, then it can predict the output

The ultimate goal is to find the hidden patterns or underlying structure in the given input data in order to learn about the data

Uses training data to learn a relationship between the input and the outputs

Does not use output data

It is a Predictive Modeling technique which predicts the future outcomes

It is a Descriptive Modeling technique which explains the hidden relationship between the data elements

More accurate results are obtained as input data and corresponding output are well known, and the software only needs to give predictions

Less accurate results are obtained as the input data are unlabeled. Thus, the software has to first understand and label the data and then give predictions

Learning method takes place offline

Learning method takes place in real time

It includes classification and regression algorithms

It includes clustering and association algorithms

Complex in Computation

Less Computational Complexity