Knowledge Discovery and Data Mining

Dawit Reda

ID# 10189420

MCIS 510 - Introduction to Database Management

10/14/2018

Milestone #5 - Propose a Data Mining Technique

Introduction

Knowledge Discovery and Data Mining (KDD) is a multidisciplinary area focusing upon methodologies for extracting useful knowledge from data and there are several useful KDD tools to extracting the knowledge. [1] This knowledge can be used to increase the quality of education.

These days, student evaluations to measure the efficiency of teachers become highly important in all universities to improve quality of education. Universities and colleges usually use the result of evaluations to monitor teaching quality and to help teachers improve their teaching effectiveness. Let’s assume that the School of Natural Sciences and Allied Health at Cabrini University needs to evaluate the performance of teachers by collecting data from student’s Student Instructional Rating Survey (SIRS) and from the university database.

The main goal of the evaluation will be predicting the teacher’s performance and determine the factors that affect the performance of the student to improve the quality of education.

To extract meaningful and valuable data, Data mining would offer promising ways to determine good patterns within a collection of data. Data mining is the process of discovering relationships, patterns by finding through a large amount of data stored in repositories, corporate databases, and data warehouses.

Data Mining Technique

There are a lot of data mining techniques that can be applied in education systems. The most common data mining used for educational evaluation purposes are clustering, classification, outlier detection, association rule mining, and sequential pattern mining. A decision tree classifier is one of the most widely used supervised learning methods used for data exploration based on divide & conquer technique [2].

Kabra [3] has also stated on his paper that decision tree would be the best choice to classify the data and evaluate a performance of teachers.

The most commonly, and nowadays probably the most widely used decision tree algorithm is C4.5 [4]. Professor Ross Quinlan developed a decision tree algorithm known as C4.5 in 1993; it represents the result of research that traces back to the ID3 algorithm (which is also proposed by Ross Quinlan in 1986). C4.5 has additional features such as handling missing values, categorization of continuous attributes, pruning of decision trees, rule derivation, and others.  Basic construction of C4.5 algorithms uses a method known as divide and conquer to construct a suitable tree from a training set S of cases (Wu and Kumar, 2009).