| Title |
Studentų akademinės sėkmės nuotolinėse studijose prognozavimo galimybės taikant duomenų tyrybą / |
| Translation of Title |
The possibilities for predicting students’ academic success in distance studies using data mining. |
| Authors |
Kukštys, Artūras |
| Full Text |
|
| Pages |
86 |
| Keywords [eng] |
academic success ; prediction ; data mining ; data mining methods and algorithms |
| Abstract [eng] |
Higher education institutions operate in a competitive market. Students’ academic performance is significant in evaluating the quality of educational institutions and has a direct impact on their reputation. The ability to forecast students’ academic success in a course or study program allows universities to take preventive measures to reduce student dropout rates. Recently, data mining techniques have been extensively used for prediction of academic success. The SWOT analysis revealed that students experience academic failure and dropout in second cycle distance studies „Information Technologies of Distance Education“ in KTU. The aim of this project is to reduce the dropout rate among distance learners by creating conditions for predicting their academic success using data mining technique. To achieve the aim, an early warning system based on data mining has been designed. This system involves a consistent and digitized monitoring of students’ academic success, helping to identify learners who are facing academic difficulties and alerting the higher education institution about them. Furthermore, the designed system includes measures to prevent students from dropping out and to support their successful completion of their studies. To assess the suitability of the system for the study program, a research was conducted. The results showed that it is possible to predict academic success using the forecasting model. Although the model can identify students that are at risk of dropping out, but it is important to refine the model to reduce the likelihood of errors and increase the accuracy of the predictions. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
Lithuanian |
| Publication date |
2023 |
