Skip to main content

An activity that seeks patterns in large, complex data sets. It usually emphasizes algorithmic techniques, but may also involve any set of related skills, applications, or methodologies with that goal.

Conceptually speaking, data-mining can be thought of as one item (or set of skills and applications) in the toolkit of the data scientist.

More specifically, data-mining is an activity that seeks patterns in large, complex data sets. It usually emphasizes algorithmic techniques, but may also involve any set of related skills, applications, or methodologies with that goal.

In US-English colloquial speech, data-mining and data-collection are often used interchangeably.

However, a main difference between these two related activities is intentionality.

Definition inspired mostly by the contributions of @statsRus to Data Science.SE