Here’s a fascinating piece from Scientific American by Larry Greenemeier. It concerns data-mining software developed by Harvard University and the Broad Institute of M.I.T. and Harvard. The software in question is a component of the Maximal Information-based Nonparametric Exploration (MINE) program.
“The software teases out relationships among data points (potentially millions of them) and measures the strength of these connections. As the researchers report in a paper appearing in the December 16 issue of the journal Science, most data-mining tools used today can either find correlations between data or determine how solid those connections are—few can do both.” [Link in original]
Greenemeier summarizes the results of the program’s initial runs on World Health Organization and Major League Baseball data. Check it out.