PREDICTING FACULTY DEVELOPMENT TRAININGS AND PERFORMANCE USING RULE-BASED CLASSIFICATION ALGORITHM

Abstract

This paper yearns for the extraction of knowledge significant for predicting training needs of newly-hired faculty members in order to devise development programs necessary to enhance faculty inherent potentials using rule-based classification data mining technique particularly sequential covering algorithm and hold-out method. In discovering significant models needed for predictive analysis, the Cross Industry Standard Process for Data Mining (CRISP-DM) was employed. Results show that professional trainings are needed in order to prepare faculty members to perform their tasks effectively.