An innovative method for data mining in higher education

Efficiency of process remains the key issue in higher education. Process efficiency is closely connected with data mining as data mining supports decision making in higher education. Development of Information and Communication Technology (ICT) has promoted the emergence of large data sets or, in other words, big data in all the areas of higher education. The aims of the research are to analyse scientific literature on innovative methods for data mining in higher education as well as to highlight advantages of the innovative method for data mining in higher education through the comparison with other methods for data mining. The methodology of the present research is built on the inter-related steps following a logical chain: analysis of scientific literature on innovative methods for data mining in higher education → comparison of innovative methods for data mining in higher education with other methods of data mining → advantages of the innovative method for data mining in higher education → conclusions. Exploratory research was employed in the present investigation. Exploratory research is aimed at generating new research questions. Interpretive paradigm was applied to the analysis. The analysis of scientific literature reveals the theoretical inter-connections between data analysis, data analytics, data mining, burstiness and gap processes. Burst detection method based on gap processes is identified as an innovative method for data mining in higher education. Such advantages of the innovative method, namely burst detection method base on gap processes, for data mining in higher education are disclosed: a realistic evaluation of burstiness in a process, and a given precision in analysing burstiness parameters/variables such as probability and concentration. Application of the burst detection method base on gap processes for data mining in higher education supports decision making for increasing efficiency in such processes of higher education as predicting student performance, planning and scheduling, enrolment management, target marketing, management and generation of strategic information, students’ selection of courses, measurement of students’ retention rate, grant fund management of an institution, optimization of study processes. Directions of further research are proposed.