So basically you see that Supervised and Unsupervised learning, both works over datasets but one of the key difference is that in supervised learning the datasets are labelled, meaning there are features(Parameters) given about the data that means we can predict some more features based on some earlier given features(experience) whereas, in unsupervised learning, the data given is not labelled, means we can not predict new features with it.
This is a type of machine learning where there is a labelled data set is given with different features in it. For instance, we have a dataset of 1 million students with two features marks scored and study time. So based on the given study time of an average student, we need to predict the marks scored by a student.
Here in unsupervised learning, the dataset is not labelled, there are no features or parameters are given. So with these types of datasets, we can only find the difference between the given data rather than predicting. It clusters the data together and shows the structure of the data. Unsupervised learning is used in the astronomical field where we can group different galaxies. Also, it is used at many other places like social media, traffic controls, etc.