KDnuggets Home » News » 2014 » Oct » News, Features » New Poll: Methodology for Analytics, Data Mining, Data Science Projects? ( 14:n27 )

New Poll: Methodology for Analytics, Data Mining, Data Science Projects?


KDnuggets revisits the question of methodology, and asks "What main methodology are you using for your analytics, data mining, or data science projects?" Please vote.



By Gregory Piatetsky, @kdnuggets, Oct 13, 2014.

CRISP-DM I was recently asked about including a 2007 KDnuggets Poll on Methodology in a book, and this prompted me to update this poll.

Methodologies like CRISP-DM and SEMMA (from SAS) seemed to decline in visibility, perhaps because they are not as well adapted to Big Data. CRISP-DM was a prominent part of early versions of SPSS Clementine, but I don't know how prominent it is in current versions of IBM Modeler.

Google Trends can barely find enough data for CRISP-DM, and Google Trends for SEMMA are not for SAS methodology but for results from Latin America (since "Semma" is a popular shopping center in Brazil and something else in Dominican Republic) .

This poll is over - here are the results of KDnuggets Poll: CRISP-DM, still the top methodology for analytics, data mining, or data science projects

Additional relevant links for methodologies:

Sign Up