Predicting Students Grades Using Artificial Neural Networks and Support Vector Machine

Predicting Students Grades Using Artificial Neural Networks and Support Vector Machine

Sajid Umair (The University of Agriculture, Peshawar, Pakistan) and Muhammad Majid Sharif (National University of Sciences and Technology (NUST), Pakistan)
DOI: 10.4018/978-1-5225-7365-4.ch059

Abstract

Prediction of student performance on the basis of habits has been a very important research topic in academics. Studies show that selection of the correct data set also plays a vital role in these predictions. In this chapter, the authors took data from different schools that contains student habits and their comments, analyzed it using latent semantic analysis to get semantics, and then used support vector machine to classify the data into two classes, important for prediction and not important. Finally, they used artificial neural networks to predict the grades of students. Regression was also used to predict data coming from support vector machine, while giving only the important data for prediction.
Chapter Preview
Top

Background

In educational environments, it is very important to predict student’s performance. To amplify a students’ performance is a long-term goal in all academic institutions in their learning environment. Now a day, data mining technique ‘Educational Data Mining’ (EDM) is used on a large-scale to automatically analyze the student’s performance and his behavioral data with learning environments. The use of text mining is a new trend in EDM that extends data mining on text data. A lot of experiments have been done in past couple of years in areas to predict students’ academic performance. A couple of methods have also been applied in Machine learning area to obtain useful/important data and for the prediction of future data trends.

Complete Chapter List

Search this Book:
Reset