Organizers:
MIPRO and University of Zagreb, Faculty of Organization and Informatics, Varaždin
Chairs:
Dijana Oreški, Irena Kedmenec, Nikola Kadoić (Faculty of Organization and Informatics, Varaždin)
Contact:
Dijana Oreški, dijana.oreski@foi.hr, Irena Kedmenec, irena.kedmenec@foi.unizg.hr, Nikola Kadoić, nikola.kadoic@foi.unizg.hr (Faculty of Organization and Informatics, Varaždin)
About:
Data is being increasingly recognized by organizations and businesses as potential for significant benefits to business and society. Data science algorithms can efficiently analyze large amounts of data. The purpose of this workshop was to give an overview of decision trees as predictive modeling technique and to explain the process of development and interpretation of the predictive model using decision tree algorithm. Basic idea was to work on data science projects with social impact. Case studies of education (Moodle log datasets) and entrepreneurship were presented.
Program:
Steps of CRISP DM methodology for development of predictive models.
Example of Moodle log analysis (data preparation and modeling).
Evaluation and interpretation of the model.
