KEFIR, developed by Gregory Piatetsky-Shapiro, Chris Matheus and Dwight McNeill, is a system for analysis and summarization of key changes in
large databases. KEFIR automatically analyzed changes in all relevant
variables, selected the important ones, and added, where possible,
expert recommendations on what to do about the changes. KEFIR
prototype was applied to all of GTE health care data and won GTE's highest technical achievement award.
KEFIR is a good example of summarization system - see module 16.
Here is KEFIR book chapter,
Selecting and Reporting What is Interesting: The KEFIR Application to Healthcare Data, C. Matheus, G. Piatetsky-Shapiro, and D. McNeill, in Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press, 1996.
Full KEFIR report is very large, and only two representative pages are included here:
