A comparative between CRISP-DM and SEMMA through the construction of a MODIS repository for studies of land use and cover change

Abstract

Among the most popular methodologies for development of data mining projects are CRISP-DM and SEMMA, This research paper explains the reason why it was decided to compare them from a specific case study. Therefore, this document describes in detail each phase, task and activity proposed by each methodology, applying it in the construction of a MODIS repository for studies of land use and cover change. In addition to the obvious differences between the methodologies, there were found other differences in the activities proposed by each model that are crucial in non-typical studies of data mining. At the same time, this research determines safely the advantages and disadvantages of each model for this type of case studies. When the MODIS product repository construction process was completed, it was found that the additional time used by CRISP-DM in the first phase was composed in the following phases, since the planning, definition of mining goals, and generation of contingency plans, allow developing the proposed phases without inconvenience. It was also demonstrated that CRISP-DM is presented as a true methodology in comparison with SEMMA, because it describes in detail each phase and task through its official documentation and concrete examples of its application.