GENDER PATTERNS FROM STUDENT ADMISSION DATA: DATA MINING FOR RELEVANT GENDER AND DEVELOPMENT INITIATIVE
Data mining functionalities have been employed to discover patterns from big data. Taking into consideration such capability, this study was conducted to employ such technique to gain insights from the university admission data. Aside from aggregation, this investigation utilized the Decision Tree and the Random Forest algorithms to predict the degree program and specialization preference. It was revealed that more of the applicants were female. From among the models generated, female preference differs basically based on their municipal residence, while male preference is attributed to their Senior High School, average grade, and municipal residence.
University Admission, Gender Pattern, Data Mining, Characterization