MIDAS is no longer active. Please, check out the Stanford database group.


Data mining is broadly defined as finding interesting patterns, structures, clusters, etc., in large amounts of data. Given this broad definition, there are many different methods developed in various fields that can be called data mining.

Fittingly, the data mining group at Stanford, called MIDAS, is an informal umbrella organization, for a variety of groups that share an interest in data mining. Even though the core of MIDAS comes from the InfoLab at Stanford, there are participants from the AI and Graphics groups as well as the Statistics and Linguistics departments.

The name MIDAS is actually an acronym for MIning Data At Stanford.

We have a weekly meeting with a varying participation. Topics range from admistrative issues and grant proposals to conference-style presentations by students and visitors.