Predictive analysis for selecting post graduate course based on students overall performance and surveillance using educational data mining

Abstract

Data mining refers to as an on trivial extraction of novel, potentially useful information and ultimately understandable patterns from a large amount of data. newlineThe hidden patterns must be actionable so that they may be used in a venture decision making process. Data mining have been applied to a numerous domains to newlinesolve the previously unsolved problems and the result has been quite promising. The academic research in Data Mining also contributed a lot to the predictive newlinetechnologies. The use of Data Mining is founded on the theory that the historical data holds essentially hidden and previously unknown knowledge that can be used newlinefor predicting the future direction and assist in decision making. newlineData mining is one of the hottest research areas nowadays as it has got wide variety of applications in common man s life to make the world a better place to live. newlineIn this research work, data mining is effectively applied to a domain called course prediction on educational data mining, since taking wise career decision is so crucial newlinefor anybody for sure. Many of the studies carried out by many researchers in various domain of education such as dropout ratio, job placement, enrolment in course, newlinestudents learning analysis, tutor interactive modules etc. newlineAt any given time, it is difficult to predict academic achievement with course selection in higher education. Instead, the primary goal of this work is to discover the newlinemethods that can better predict the best course of research for further study. For this reason, we chose some Data Mining techniques and attempted to predict the newlinebest course range for students. The success of any data mining process depends highly on data selected for operation. For a classification problem, attributes that are newlinehaving very good discriminative power should be selected and feature selection method used for affected parameters in research study.