Supervised learning is a class of machine learning algorithm that takes in a series of vectors and their corresponding output (a continuous value or a class) as input, and produces an inferred function that can be used to map new examples.
An important precondition for using supervised learning is the availability of labeled data. In other words, it is necessary that we have access to input for which we already know the correct output.
Supervised learning can be classified into two types: classification and regression. A classification problem has a discrete set of values as the target variable (for instance, a like and a dislike), whereas a regression problem has a continuous value as its target (for instance, an average rating between one and five).
Consider the rating matrix defined earlier. It is possible to treat (m-1) columns as the input and the mth...