DATA MINING APPLICATION FOR DETERMINING STUDENTS’ ACADEMIC PERFORMANCE
Need help with a related project topic or New topic? Send Us Your Topic
DOWNLOAD THE COMPLETE PROJECT MATERIAL
DATA MINING APPLICATION FOR DETERMINING STUDENTS’ ACADEMIC PERFORMANCE
GENERAL INTRODUCTIONS
1.1 Introduction
Data mining is a discipline of computer science that deals with the process of extracting patterns from big data sets using statistical and artificial intelligence approaches along with database administration.
Data mining is viewed as an increasingly crucial technique by modern businesses for transforming data into business insight, providing an information advantage. It is being employed in a variety of profiling applications, including marketing, surveillance, fraud detection, and scientific discovery. [Clifton, 2010.]
The words data dredging, data fishing, and data snooping all refer to the use of data mining techniques to sample areas of a larger population data set that are (or may be) too tiny to make solid statistical judgements about the validity of any identified patterns. However, these strategies can be utilised to generate new hypotheses for testing against larger data sets. [Clifton, 2010.]
Performance monitoring includes assessments, which play an important role in giving information to students, teachers, administrators, and policymakers to help them make decisions.[Counsil, 2001].
The changing factors in contemporary education have resulted in a desire to effectively and efficiently monitor students’ performance in educational institutions, which is now shifting away from traditional measurement and evaluation techniques and towards the use of Data Mining Techniques, which employ various intrusive data penetration and investigation methods to isolate vital implicit or hidden information.
Because various new technologies have contributed and generated vast volumes of explicit knowledge, implicit knowledge has gone unnoticed and is buried behind massive amounts of information.
The primary feature of data mining is that it encompasses Knowledge Discovery, which, according to Frawley (1991), is a nontrivial process of identifying valid, novel, potentially useful, and ultimately understandable patterns in data processes, thereby contributing to predicting trends in outcomes by profiling performance attributes that support effective decision making.
This project applies data mining theory and practice to the performance and monitoring of students at Kwara State Polytechnic in Ilorin, Nigeria.
Technological advancements and new programming techniques have increased our knowledge and application of artificial intelligence (AI). The separation of hidden data and exposed relationships embedded within it
without prior knowledge of the nature of any inherent relationship, leads [Rubenking 2001] to assert that data mining is a logical evolution of database technology.
With the development of enhanced query tools such as SQL, database managers can query data more flexibly. Rules produced from diverse algorithms during the application of Data Mining Tools in study support this viewpoint.
Recently, educational institutions have used computer-based systems to manage and retain massive amounts of data generated throughout educational processes in search of hidden patterns.
The face value assessment of students at the point of entry can only be confirmed or refuted by dynamic follow-up monitoring of students’ performance during the course of study, which serves as an indicator of students’ suitability and unsuitability before admission and throughout their course of study.
Fuzzy Set Theory is employed in applications involving educational assessment and performance since it is considered efficient and effective in uncertain conditions requiring performance assessment.
It is well known that expert fuzzy scoring systems, as reported by Nolan (1998), assist teachers in making assessments in less time and with a degree of accuracy comparable to the finest teacher examiner.
This report profiled students based on factual and partially behavioural characteristics. Gender, date of birth, race, and other details, such as college test results for each semester, are retrieved from student records.
Performance profiling is based on motivation, attitudes, peer influence, curriculum, and ongoing real-time monitoring of student performance using a simple rapid response system, and as [Luan 2001] noted, it accurately predicts which students may require additional attention or reinforcements during their education.
The created methodology contributes to a measurable student progress monitoring procedure that yields results rapidly and achieves a bigger educational goal that benefits stakeholders in the educational system and the wider community.
Need help with a related project topic or New topic? Send Us Your Topic