Regression is another main instance of supervised learning in machine learning. Given a training set of data containing observations and their associated continuous outputs, the goal of regression is to explore the relationships between the observations (also called features) and the targets, and to output a continuous value based on the input features of an unknown sample.

The major difference between regression and classification is that the outputs in regression are continuous while discrete in classification. This leads to different application areas for these two supervised learning methods. Classification is basically used in determining desired memberships or characteristics, as we have seen in previous chapters, such as email being spam or not, news topics, and ad being clicked-through or not. Regression mainly involves estimating an outcome or forecasting a response.

Examples of machine learning regression include:

• Predicting house prices based on location, square footage, and number of bedrooms and bathrooms
• Estimating power consumption based on information of a system's processes and memory
• Retail inventory forecasting
• And of course, stock price prediction