Supervised learning mainly uses two important types of data: labeled data and features. To understand how supervised learning works, it’s key to know about these two types.

Labeled Data
Labeled data is made up of pairs that include input data and matching outputs, which are called labels. These labels tell the model the right answer or category it needs to learn.
For example, if we are teaching a model to identify pictures, the images would be the input data, and the labels would be the names of things in those images, like “cat” or “dog.”
Labeled data is important because it sets supervised learning apart from unsupervised learning, where there are no labels to guide the model.

Features
The second important part is features. Features are the measurable traits or details of the data. They help show the different aspects of the input data that are important for learning.
For instance, if we are looking at house prices, features could include things like the size of the house, the location, the number of bedrooms, and how old the house is.
Each feature helps the model make better predictions based on patterns it learns from the labeled data.

In Summary
Good supervised learning depends on having high-quality labeled data and useful features.
These two parts work together to help models learn from past data and make accurate predictions about new data they haven’t seen before. This helps improve many areas like classification and regression.