Prediction System for Student Performance Using Data Mining Classification

In the education system, highest level of quality can be achieved by exploring the knowledge regarding prediction about student's performance. In an analysis of data, data mining techniques play an important role. In order to predict performance of students in future academics, it's good if an educational institution have an approximate prior knowledge of all enrolled students in their institute. This prior knowledge becomes an important tool for educational institute to improve students those who would likely to get less marks and also identify bright student. As a solution we are trying to develop a system which will help an educational institute to prefigure the performance of students from their former functioning. In order to achieve this we will use concepts of data mining techniques under Classification. Also for solution to get developed we are trying to prepare the data set containing information about students in terms of their gender, marks and rank in entrance examinations and results in Third year of the former batch of students. These data sets have been analyzed to prepare final solution. The mapping of data into predefined groups or classes is done in Classification data mining technique. It is a supervised learning method in which to generate rules for classifying test data into predetermined groups or classes labeled training data is required. The process is divided into two-phases. The first phase which is learning phase, the training data is examined and classification rules are begot in this phase. The second phase the Classification one in which test data is classified into classes in accordance with training data set. General and individual performance of third year students in future examinations is prefigured by using the ID3 (Iterative Dichotomize 3), C4.5, Improved weighted modified ID3 classification algorithms on this data.