Performance Analysis of Students Consuming Alcohol Using Data Mining Techniques
International Journal of Advance Research in Science and Engineering, Vol. 6, Issue. 2, February 2017, pg.238-250
13 Pages Posted: 26 Jun 2017 Last revised: 30 Jun 2017
Date Written: June 23, 2017
Alcohol consumption in higher education institutes is not a new problem; the legal drinking age in the India is minimum 18 year, but heavy drinking by underage students and by those who are age 18 or older is dangerous, and disruptive. Excessive drinking among students is associated with a variety of negative consequences that include fatal and nonfatal injuries; alcohol poisoning; blackouts; academic failure; violence, including rape and assault; unintended pregnancy; sexually transmitted diseases, including HIV/AIDS; property damage; and vocational and criminal consequences that could jeopardize future job prospects. Because students vary widely in their drinking rates, it would be inaccurate to characterize all institutions as having an equally urgent drinking problem. But among students who do drink heavily, the problem is serious: the two out of five students who engage in binge drinking risk a wide range of alcohol-related consequences, including grave injuries and death. This paper describes four popular data mining algorithms Sequential minimal optimization (SMO), Bagging, REP Tree and decision table (DT) extracted from a decision tree or rule-based classifier to improve the efficiency of academic performance in the educational institutions for students who consume alcohol. In this paper, we present a real-world experiment conducted at VBS Purvanchal University, Jaunpur, India. This method helps to identify the students who need special advising or counseling by the councilors/teachers to understand the danger of consuming alcohol.
Keywords: Alcohol Consumption, Sequential Minimal Optimization (SMO), Bagging, REP Tree, Decision Table.
Suggested Citation: Suggested Citation