Data Mining Report Final

EBC6220: Data Mining For Business Application

An Overview of Mining Educational Data to analyze Student Performance

[pic 1]

Group Presentation Report

Professor: Nancy Samaan

Submitted by:

Date of Submission: 12th December, 2014

Table of Contents

ABSTRACT1

INTRODUCTION1

OBJECTIVES OF EDUCATIONAL DATA MINING 2

USE OF DATA MINING IN EDUCATION 4

DATA MINING TECHNIQUES 6

DATA MINING PROCESS 10

ADVANTAGES OF EDUCATION DATAMINING…………………………………………12

CASE STUDY…………………………………….……………………………………………..13

CONCLUSION…………………………………………………………………….……………15

BIBLIOGRAPHY…………………………………………………………………………….…16

ABSTRACT

The main objective of the educational organization is to provide quality education to its students. One way to achieve the highest level of quality in higher education is by discovering knowledge for prediction on enrollment of students in a particular course, unfriendliness model in the traditional classroom teaching, recognition of unfair means used online examination, discovery of abnormal values in the result students leaves, prediction on the performance of students and so on. Knowledge is hidden among the set of educational data and can be extract by using data mining techniques.

In our report we will discuss the capabilities of data mining techniques in the context of education and how it is used to evaluate student performance. In this report we will discuss that which techniques and algorithm are used to evaluate the performance of students and how it helps earlier in recognizing the dropouts and students who want special attention and also help teachers to give appropriate advising and counseling.

INTRODUCTION

Data mining, also called as Knowledge Discovery in Databases (KDD), it is the platform of determining original and useful information from huge volumes of data. Data mining has been utilizing in education which is also called as Educational Data Mining (EDM), it concerns with emerging approaches that determine knowledge from data originating from educational environments. EDM refers to the interpretation of a wide range of data produced by and gathered on behalf of students in order to assess academic development, predict and identify future performance, and spot prospective concerns. Data are gather from student engagements, such as finalizing assignments and taking exams and tests, from implied actions, containing online social communications, extracurricular activities, posts on conversation forums, and other activities that are not directly assessed as part of the student’s educational improvement. Examine simulations that process and demonstrate the data assist faculty members and school personnel in understanding. The goal of wisdom analytics is to empower teachers and schools to tailor educational opportunities to each student’s level of need and ability. (Baker, 2011) deliver researchers in educational environment with opportunities to use data mining for investigation and examination. Reducing from and building on the pitch of data mining in educational settings, performance Analytics and emphases on gathering, measuring, and analyzing data about students and their learning performance for the determination of optimizing learning performance. In modern years there has been an increased importance in using data mining for educational purposes. A very comprehensive review of data mining in education from 1995 to 2005 is published in 2007 by Romero and Ventura. One of the educational problems that are resolved with data mining is the analyzing of students' academic performances, whose goal is to identify an unknown variable (outcome, grades or scores) which describes students. The assessment of students' performances includes observing and supervisor students through the teaching process and assessment. Assessments, as the main process for the measuring studying outcomes, highlighted the level of students' performance. Therefore, exams play a vital role in any student’s lives, significant their future. Minaei-Bidgolim, et al. (2003) was amongst the first authors who categorized students by using genetic algorithms to analysis their final grade. Applying the progression methods, Kotsiantis and Pintelas (2005) predicted and analysis student’s marks (pass and fail classes). Superby, Vandamme and Meskens (2006) analysis student’s academic achievements (classified into low, medium, and high risk classes) utilizing different data mining methods (decision trees and neural network). Kumar and Vijayalakshmi (2011) using the decision tree predicted and analysis the result of the final exam to help tutors identify those students who needed help, for improve their performance and pass the exam.