Machine learning represents one of the fundamental areas of artificial intelligence and deals with the creation of systems and algorithms that analyze a large amount of data for the synthesis of new knowledge.
Machine Learning systems are able to learn from experience, where experience means the ability of a system to capture characteristics of interest from examples, data structures and sensors, with the aim of analyzing them and evaluating the relationships between variables.
Extracting “hidden” information from existing data structures falls within the scope of data mining, which has long provided techniques and methodologies for extracting useful information from a set of data.
Machine Learning differs from data mining, as the purpose in this case is to create systems capable of learning from data, based on the principle of the generalization of algorithms, ie the ability to work in new situations, after a “training” on a first set of data.
In recent years, the great popularity of MOOCs has forced educational researchers to tackle problems that just a few years earlier could not be imagined.
Given the amount of data sets produced by MOOCs, techniques and methodologies developed in the field of Machine Learning had to be adopted in order to be able to provide a more accurate prediction of student behaviors and results.