Tools used to predict future information by learning patterns and then applying them to predict future relationships. According to Berry and Linoff (1997), neural networks are the most common type of data mining technique. Neural networks attempt to learn patterns from data directly by repeatedly examining the data to identify relationships and build a model. They build models by trial and error. Neural networks are a form of multiprocessor hardware or software system inspired by biological systems. They often feature simple processing elements with a high degree of interconnection.