Data mining (DM) can be described as a tool set for, or process of, discovering knowledge (more or less automatically) from observational data sets. It is interdisciplinary in that it combines concepts and approaches from fields that include database technology, machine learning, statistics, data visualization, pattern recognition, and optimization. The progressive gathering of very large and heterogeneous data sets, accompanied by the increasing computational power and evolving database technologies, has generated an increasing interest in DM. In addition to technological advances, the success of DM—at least in corporate environments—can also be attributed to changes in the business environment. Many factors have created a need on the part of these companies for enhanced insight, understanding, and actionable plans that allow them to systematically manage and deepen customer relationships. These factors include increased competition because of the advent of electronic commerce, removal of barriers for new market entrants, more informed and thus demanding customers, and increased saturation in many markets. Insurance companies try to identify those individuals who are most likely to purchase additional policies, retailers seek those customers who are most likely to respond to marketing activities, and banks want to determine the creditworthiness of new customers to offer them attractive products. These organizations also try to improve their churn prediction performance using data-driven methods.