CHAPTER ONE
INTRODUCTION
1.1 General Overview
In recent years, the technology of database has become more advanced where large amount of information is required to be stored in the databases. data mining then attract more attention to extract valuable information from the raw data that institution can use for decision-making process. It applies modern statistical and computation technologies to expose useful information hidden within the large database to remain competitiveness among educational field, the institution need deep and enough knowledge for a better assessment, evaluation, planning and decision-making. Data mining helps institution to use their current reporting capabilities to discover and identity the hidden patterns in database and hence can be used to predict performance of the student. Data mining can be viewed as a result of the natural evolution of information technology because before 1960 when database and information technology had not evolved, analysis of data was basically the primitive file processing which would not give the appropriate useful information despite the huge amount of time consumed. The evolutionary path of data mining has been witnessed in the database industry in the development of the following database and information technology.
1. data collection and data creation
2. informatin management (including data warehouse and information preparation)
3. information analysis and understanding (involving data mining and information interpretation) Moreover, data mining is also known as knowledge discovery in large information base (KDD). Consequently, information mining consist of more than collecting and managing information; it also includes analysis and predictions. Important decision are often made based not on the data rich information stored in data base but rather on decision maker’s institution, simply because maker does not have the tools to extract the valuable knowledge embedded in the vast amount of information.
1.2 Statement of the problem
It is not feasible for people to analyze great amounts of data without the assistance of appropriate computational tools. Therefore, the development of tools of an automatic and intelligent nature becomes essential for analyzing, interpreting, and correlating information in order to develop and select strategies in the context of each application. To serve this new context, the area of Knowledge Discovery in Databases (KDD), came into existence with great interest within the scientific, industrial, and commercial communities. The popular expression “Data Mining” is actually one of the stages of the Discovery of Knowledge in Databases. The term “KDD” was formally recognized in 1989 in reference to the broad concept of procuring knowledge from databases. One of the most popular definitions was proposed in 1996 by a group of researchers. According to Fayyad, et al. (1996): “KDD is a process with many stages, non-trivial, interactive, and iterative, for the identification of comprehensible, valid, and potentially useful patterns from large data sets”. It is of utmost desire to extract valuable information from large databases. This research work therefore addresses the intelligent prediction of students’ course of study in higher institution based on the historical student academic data. This will facilitate better performance of students in high institutions.
1.3 Aim and Objectives of the Project
1.3. 1 Aim
The aim of the research work is to develop a computer application software that will be able to predict student course of study in higher institution using classification algorithm.
1.3. 2 Objectives
The following are the set of objectives addressed by the project work:
1. To develop and populate student academic database
2. To develop a computer application program that will be able to mine knowledge from the students’ academic database using Classification algorithm.
3. To predict student course of study according to their Post UTME cutoff.
4. To reduce the rate at which student admission is fortified.
1.4 Research Methodology
The executive of execution of research work includes the following;
1. analysis of some data mining techniques i.e. data mining techniques yield the benefit of automation on existing software and hardware platforms, can be implemented on new system as existing platform are upgraded and new products developed.
2. consideration of sources data record i.e. the admission office student database and the department student database.
3. consultation with some database developers or technologist.
4. browsing on internet to get access to some websites for relevant information.
5. consultation with some professional statistical analyst
1.5 Significant of the Study
The use of data mining technique in predicting student course of study is very significant and relevant in any academic institution where record of each student has been collected and stored in a database e.g system the need for knowledge discovery in academic environment may be at admission level or faculty level. The institution may want to know from which mode of admission does they have student with better result. The institution may want to know the student performance in general courses and reason for such performance. The institution may want to predict the number of student that is to be admitted to specific department and faculty so as to allocate reasonable amount of resources to various departments for the session
1.6 Scope of the Study
The research work has been centered on only ‘O’ level, pre degree or UTME science courses only.
1.7 Limitation of the study
The research work is limited to the Faculty of Science and Engineering of Osun State Polytechnic, IREE.
1.8 Data mining review
Data mining is process of extract hidden pattern from data. As more data is gathered, with the amount of data doubling every three years, data mining is becoming an increasingly important tool to transport this data into information. It is commonly used in a wide range of profiling practices, while data mining can be used to uncover patterns in data samples, it is important to be aware that the use of non representative sample of data may produce results that are not indicative of domain. Similarly, data mining will not find pattern that may be present in the domain, if those was mined, there is a tendency for insufficiently knowledge consumer of the result to attribute magical abilities to data mining, treating the techniques as a sort of all seeing crystal.
