Data mining is concerned with the analytical observation of patterns, relationship and dependencies that exist in a data store. This is done through the use of several techniques from artificial intelligence, programming and data management. Observations, patterns and trends derived from this process can serve as the "needed experience" for the machine learning process.

Machine learning on the other hand is a branch of Artificial Intelligence that deals with the design and development of algorithms that are fed into computers, allowing these computers to evolve behaviors based on empirical data such as databases. These algorithms help these computer systems to improve their decision making abilities based by their trainings on experiences acquired through the data mining.Machine learning algorithms aid the learning process by controlling the search through a space of possible hypotheses or solutions to find and build the knowledge structures. The algorithms extract useful information from training examples.

Unlike data mining, machine learning is built upon known patterns in a given data set; data mining lies on the discovery of unknown patterns.

This research presents some data mining procedures used to discover patterns in basket ball game data. These results from such procedures can be used in the machine learning process to build machines capable of predicting the events of basketball games as well as the outcome of each event. To learn more about the research, click here