摘要

This paper is concerned with the problem of improving undergraduate mathematical modelling competence in the current big data world. Firstly, we review the renowned teacher's seven-step, student's four-step and a six-step modelling cycles to explain mathematical modelling competence. The six-step modelling cycle is also used in Common Core State Standards for Mathematics (CCSSM) in the United States. Based on these previous modelling cycles, we propose a new five-phase modelling cycle by use of the tool named IBM SPSS Modeler in accordance with Cross Industry Standard Process for Data Mining (CRISP-DM). A teaching case will be presented to apply these methodologies to undergraduates' mathematical modelling lessons. It is shown that teachers can use IBM SPSS Modeler to improve student's mathematical modelling competence by understanding and practicing the process of five-phase modelling.