Machine Learning Techniques: A Review of Predicting Student’s Performance
Abstract
This comprehensive abstract discusses various facets of Machine Learning, focusing on its significance in the context of education and academic performance prediction. The abstract begins by highlighting the data-driven era brought about by the internet and digitization, underscoring how the abundance of data has given rise to the concept of Machine Learning. It emphasizes Machine Learning as a critical aspect of artificial intelligence that empowers systems to learn autonomously from data, without explicit programming. The abstract further delves into the educational sector’s reliance on students’ performance, emphasizing the importance of various factors in assessing academic success. It then introduces the objectives of a proposed systematic review, including identifying gaps in predictive methods and attributes for analyzing students’ performance. Supervised Learning, for instance, is detailed along with its essential components such as labeled data, the training phase, prediction phase, and evaluation. It highlights real-world applications, from spam detection to customer churn prediction, demonstrating the versatility and widespread use of supervised learning in various industries. Subsequently, the abstract transitions to Unsupervised Learning, explaining its role in clustering and association, and how it is used in customer segmentation, image segmentation, and anomaly detection, among other applications. It introduces pre-trained models, fine-tuning, domain adaptation, types of Transfer Learning, and its applications in computer vision, natural language processing, healthcare, autonomous driving, recommendation systems, and more. The abstract further explores the role of Machine Learning in academia. Now a days, most of the educational bodies are used Machine Learning techniques to make improvement in their system. Performance of the students is analyzed by using these techniques and help to students in improving their performance. Therefore, a systematic review of all papers related to this field is needed to understand the Machine Learning techniques in education and how to predict the performance of students.
References
2. McCrea N. An introduction to machine learning theory and its applications: A visual tutorial with examples. Διαθέσιμο στην ηλεκτρονική διεύθυνση: https://www. toptal. com/machine-learning/machine-learning-theoryan-introductory-primer [Τελευταία πρόσβαση 19 Μαΐου 2020]. 2016 Aug.
3. Bin Mat U, Buniyamin N, Arsad PM, Kassim R. An overview of using academic analytics to predict and improve students' achievement: A proposed proactive intelligent intervention. In2013 IEEE 5th conference on engineering education (ICEED) 2013 Dec 4 (pp. 126-130). IEEE.
4. Abed AA, El-Halees AM. Detecting Subjectivity in Staff Perfomance Appraisals by Using Text Mining. In2017 Palestinian International Conference on Information and Communication Technology 2015 Nov.
5. What Is AI? Learn About Artificial Intelligence. Retrieved from https://www.oracle.com/artificial-intelligence/what-is-ai/
6. DifferenceBetween.net. (n.d.). Differences Between Supervised Learning and Unsupervised Learning. Retrieved from http://www.differencebetween.net/technology/differences-between-supervised-learning-and-unsupervised-learning/
7. Fok WW, He YS, Yeung HA, Law KY, Cheung KH, Ai YY, Ho P. Prediction model for students' future development by deep learning and tensorflow artificial intelligence engine. In2018 4th international conference on information management (ICIM) 2018 May 25 (pp. 103-106). IEEE.
8. Aly WM, Hegazy OF, Rashad HM. Automated student advisory using machine learning. International Journal of Computer Applications. 2013;975:8887.
9. Guo B, Zhang R, Xu G, Shi C, Yang L. Predicting students performance in educational data mining. In2015 international symposium on educational technology (ISET) 2015 Jul 27 (pp. 125-128). IEEE.
10. Singh M, Singh J. Machine Learning Techniques for prediction of subject scores: A Comparative Study. International Journal of Computer Science and Network. 2013 Aug;2(4):77-9. https://pdfs.semanticscholar.org/2368/3634d0999020d6a90bf79fa605ceebe90891.pdf
11. Kumar J, Vashistha R, Kaur K, Singh SK. Machine Learning Techniques of Predicting Student's Performance. In2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT) 2023 Jun 9 (pp. 693-698). IEEE.
12. Sahlaoui H, ABDELLAOUI ALAOUI EA, Agoujil S. A framework towards more accurate and explanatory student performance model. InProceedings of the 4th International Conference on Networking, Information Systems & Security 2021 Apr 1 (pp. 1-8).
13. Bergin S. Statistical and machine learning models to predict programming performance (Doctoral dissertation, National University of Ireland Maynooth).
14. Mishra T, Kumar D, Gupta S. Mining students' data for prediction performance. In2014 Fourth International Conference on Advanced Computing & Communication Technologies 2014 Feb 8 (pp. 255-262). IEEE.
15. Han M, Tong M, Chen M, Liu J, Liu C. Application of ensemble algorithm in students' performance prediction. In2017 6th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) 2017 Jul 9 (pp. 735-740). IEEE.
16. Sungar VA, Shinde PD, Rupnar MV. Predicting Student’s Performance using Machine Learning. Commmications on Applied Electronics. 2017 Dec;7(11):11-5.
17. Mahboob T, Irfan S, Karamat A. A machine learning approach for student assessment in E-learning using Quinlan's C4. 5, Naive Bayes and Random Forest algorithms. In2016 19th international multi-topic conference (INMIC) 2016 Dec 5 (pp. 1-8). IEEE.
18. Tanuar E, Heryadi Y, Abbas BS, Gaol FL. Using machine learning techniques to earlier predict student's performance. In2018 Indonesian Association for Pattern Recognition International Conference (INAPR) 2018 Sep 7 (pp. 85-89). IEEE.
19. Solis M, Moreira T, Gonzalez R, Fernandez T, Hernandez M. Perspectives to predict dropout in university students with machine learning. In2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI) 2018 Jul 18 (pp. 1-6). IEEE.
20. Pushpa SK, Manjunath TN, Mrunal TV, Singh A, Suhas C. Class result prediction using machine learning. In2017 International Conference on Smart Technologies for Smart Nation (SmartTechCon) 2017 Aug 17 (pp. 1208-1212). IEEE.
21. Gerritsen L, Conijn R. Predicting student performance with Neural Networks. Tilburg University, Netherlands. 2017 May.
