# Educational Data Mining and Learning Analytics - Educational Assistance for Teaching and Learning

**Authors:** Ms. Ganesan Kavitha, Dr. Lawrance Raj  
**arXiv:** [1706.03327](https://arxiv.org/abs/1706.03327)  
**Date:** 2017-06-11  
**Summary page:** https://www.summarizepaper.com/en/paper/1706.03327v1/

## Key points

- Teaching and learning process in educational institutions requires constant monitoring and analysis for enhancement
- Accreditation agencies have set criteria for teaching and learning, making it essential to ensure that students are progressing well
- Learning analytics and Educational Data Mining (EDM) are relatively new techniques used to collect large volumes of data about students in an educational setting to predict their future performance and identify risks
- EDM develops methods to analyze the data produced by students in educational settings, helping educators understand their students' needs better
- The proposed research aims to collect a vast amount of data on student performance in assessments to discover those at risk of failing the final exam
- Educators can gain insights into how students are progressing and identify those who need additional support through analyzing this data
- The study will focus on collecting and analyzing assessment results at the course level to enhance the teaching and learning process
- Decision tree classification technique was used on student assessment outcome databases to identify those who need support to perform well in their final exams
- This approach can help teachers/instructors find out how well their students are doing while also identifying areas where they may need additional support.
- Overall, this research aims to improve student retention rates by enhancing the teaching and learning process through data-driven insights provided by EDM techniques such as decision tree classification.

## Summary

The teaching and learning process in educational institutions is a vital element that requires constant monitoring and analysis for enhancement. Accreditation agencies around the world have set criteria for teaching and learning, making it essential to ensure that students are progressing well. Learning analytics and Educational Data Mining (EDM) are relatively new techniques used to collect large volumes of data about students in an educational setting to predict their future performance and identify risks. EDM develops methods to analyze the data produced by students in educational settings, helping educators understand their students' needs better. This research aims to collect a vast amount of data on student performance in assessments to discover those at risk of failing the final exam. By analyzing this data, educators can gain insights into how students are progressing and identify those who need additional support. The proposed research will utilize the results of the analysis to provide recommendations for improvement, including identifying at-risk students. The study will focus on collecting and analyzing assessment results at the course level to enhance the teaching and learning process. Two feature selection techniques, information gain, and gain ratio were discussed in detail with gain ratio being adopted as the feature selection technique. In this paper, decision tree classification technique was used on student assessment outcome databases to identify those who need support to perform well in their final exams. This approach can help teachers/instructors find out how well their students are doing while also identifying areas where they may need additional support. Overall, this research aims to improve student retention rates by enhancing the teaching and learning process through data-driven insights provided by EDM techniques such as decision tree classification. By identifying at-risk students early on, educators can provide targeted support that helps them succeed academically while improving overall student outcomes.