Abstract

OGOSI AUQUI, José Antonio; LIRA CAMARGO, Jorge; VERA TITO, Francisca Sonia  and  LEON-VELARDE, César Gerardo. NEW CSKT METHODOLOGY TO IMPROVE MACHINE LEARNING IMPLEMENTATION PROJECTS IN INDUSTRIAL ENGINEERING AT A PUBLIC UNIVERSITY. Aula Virtual [online]. 2025, vol.6, n.13, e461.  Epub June 19, 2025. ISSN 2665-0398.  https://doi.org/10.5281/zenodo.15102636.

The research proposes a methodology taking the best parts of the CRISP-DM, SEMMA, KDD and TDSP approaches, for this first a systematic review was conducted, it was oriented to a business approach, taking into consideration the guidelines of data mining, in the process of pilot validation was conducted in a public university to assess the satisfaction of the proposed model, obtaining 67%, which implies that the model has many opportunities to improve and mature to achieve a reference model. Despite having been implemented within the Industrial Engineering career, it was determined that the model can achieve the same or better results in a public or private company. The model allows to show the activities to follow with a business approach and to become a reference for Machine Learning implementations.

Keywords : Reference model; Machine Learning; Implementation; CSKT Methodology; Enterprises.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )