International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 07 | July 2023
p-ISSN: 2395-0072
www.irjet.net
A Study on Data Mining Techniques, Concepts and its Application in Higher Education Shilpa K1,2, Dr. Krishna Prasad3 1Research Scholar, College of Computer Science and Information Science,
Srinivas University, Mangalore, India.
2Asst. Professor, Dept. of Computer Science, Nrupatunga University, Bangalore, India.
3Associate Professor & Post-Doctoral Research Fellow, College of Computer Science and
Information Science, Srinivas University, Mangalore, Karnataka, India. ---------------------------------------------------------------------***--------------------------------------------------------------------information from unstructured data. Generally speaking, Abstract - Higher education is one of many fields where data
there are two basic categories for data mining techniques: descriptive and predictive. The main goal of descriptive data mining techniques is to summarize and visualize data in order to identify patterns and trends. Among these methods are clustering, which compiles related data objects, and association rule mining, which reveals dependencies and connections between various data properties [2].
mining techniques have become crucial tools. They are used to glean important insights from large amounts of educational data. An overview of data mining methods, ideas, and specific applications in the context of higher education is given in this study. The study looks at various data mining methods that are frequently used in higher education. These methods consist of categorization, clustering, mining association rules, and mining sequential patterns. The paper explores how each strategy might be used to solve certain difficulties in higher education. In addition, the article explores data mining's use in higher education. It examines a number of crucial fields where data mining has been shown to be useful, including student performance analysis, course recommendation systems, dropout prediction, and curriculum modification. It emphasizes how these applications can improve student engagement, educational outcomes, and institutional effectiveness. The proposed work also discusses the problems and ethical issues that arise when using data mining in higher education. In order to ensure that student confidentiality and institutional standards are honored, it highlights the importance of privacy protection, data security, and responsible use of mined information.
While developing models that can classify or make predictions based on historical data, predictive data mining techniques try to do the opposite. To categorize or classify data examples, classification methods like decision trees and support vector machines are used. Additionally, regression analysis can be used to anticipate continuous variables and time series analysis to forecast future trends when creating predictive models. Techniques for extracting knowledge from various educational data sources have proven to be useful in the field of higher education [3]. Student information systems, learning management systems, online resources, social media, and research databases are some of these sources. Educational institutions can learn more about the behavior of their students as well as their learning habits, academic achievement, and engagement by evaluating this data. Data mining is used in higher education in a variety of ways. Student performance analysis is one important area where data mining techniques can be used to pinpoint variables that affect students' achievement, spot warning signals of academic problems early on, and tailor interventions to help struggling students. Data mining can also aid in the creation of systems that help students choose courses that are in line with their interests, academic objectives, and performance histories [4].
Key Words: Data mining, higher education, classification, clustering, data security.
1. INTRODUCTION By allowing the extraction of useful insights from huge amounts of data, data mining techniques have transformed a number of industries. The wealth of data produced by college students, academic staff, and educational institutions offers a singular opportunity to use data mining techniques to enhance teaching methods, student results, and institutional effectiveness. This introduction gives a general overview of data mining methods, ideas, and the particular uses to which they might be put in the context of higher education [1]. Data mining, commonly referred to as knowledge discovery in databases (KDD), is a group of computational methods and algorithms used to glean patterns, connections, and hidden information from sizable datasets. Utilizing statistical, mathematical, and machine learning techniques, it entails the extraction of pertinent
© 2023, IRJET
|
Impact Factor value: 8.226
Additionally, data mining tools allow for the forecasting of student dropout rates, allowing institutions to take preventative action to reduce attrition. Institutions can identify students who are at danger of dropping out by examining previous data patterns and can then offer them targeted support to increase their retention and graduation rates. Furthermore, data mining can help with curriculum design optimization by identifying course prerequisites, relationships between courses, and areas for curriculum enhancement based on pupil performance and feedback.
|
ISO 9001:2008 Certified Journal
|
Page 777