No abstract

No abstract

Data mining is a new approach for education. The main objectives of higher education institutions are to provide quality education to its students for their better placement opportunity. We could use Decision tree algorithms to predict student selection in placement. It helps us to identify the dropouts of the student who need special attention and allow the teacher to provide appropriate placement training. This paper describes how the different Decision tree algorithms used to predict student performance in placement. In the first step we have gathered the last two years passed out students details from placement cell in Dr.N.G.P Arts and Science College. In the second step preprocessing was done on those data and attributes were selected for prediction and in the third step Decision tree algorithms such as ID3, CHAID, and C4.5 were implemented by using Rapid Miner tool. Validation is checked for the three algorithms and accuracy is found for them. The best algorithm based on the collected placement data is ID3 with an accuracy of 95.33%.

A majority of contribution in the domain of rule mining overemphasize on maximizing the predictive accuracy of the discovered patterns. The user-oriented criteria such as comprehensibility and interestingness are have been given secondary importance. Recently, it has been widely acknowledged that even highly accurate discovered knowledge might be worthless if it scores low on the qualitative parameters of comprehensibility and interestingness. This paper presents a classification algorithm based on evolutionary approach that discovers comprehensible and interesting in CNF form in which along with conjunction in between various attributes there is disjunction among the values of an attribute. A flexible encoding scheme, genetic operators with appropriate syntactic constraints and a suitable fitness function to measure the goodness of rules are proposed for effective evolution of rule sets. The proposed genetic algorithm is validated on several datasets of UCI data set repository and experimental results are presented which clearly indicate lower error rates and more comprehensibility across a range of datasets. Some of the rules show the interesting and valuable nuggets of knowledge discovered from small disjuncts of high accuracy and low support which are very difficult to capture otherwise.

No abstract