Student Performance Prediction using Educational Data Mining

Abstract

Artificial intelligence (AI) is instigating a profound shift in education. This enhancement promotes a greater comprehension of student performance and allows for the identification of at-risk individuals who may disengage from school. This study investigates the utilization of artificial intelligence-based learning analytics to assess student achievement and dropout rates through the analysis of attendance patterns, online engagement, and levels of interest. This research will employ data from massive open online courses (MOOCs), digital learning tools, and university databases to illustrate how artificial intelligence might aid students in sustaining their development through timely interventions. This may be achieved by scrutinizing the evidence. Thus, it is probable that these therapies will include suggestions for adaptive learning and personalized feedback. The aim is to aid educators in making informed choices, promote student achievement in academic environments, and decrease the dropout rate. This will be achieved with the support of a trustworthy and principled artificial intelligence model. This project will investigate data security, bias mitigation, and the enhancement of transparency to enable the appropriate application of AI in educational institutions. Our research aims to improve the adaptability, effectiveness, and accessibility of education for all students.

Introduction

1. Blockchain-Based E-Voting System (Summary)

The text presents a secure electronic voting system that uses blockchain technology and biometric authentication (fingerprint and facial recognition) to improve election security, transparency, and trust. It addresses issues in traditional and existing e-voting systems such as centralization, weak authentication, duplicate voting, and lack of transparency. Votes are encrypted and stored on a blockchain, ensuring immutability and preventing tampering. Smart contracts enforce election rules like “one voter, one vote,” while real-time monitoring and result updates improve efficiency. The system includes admin tools for managing elections and voters. Overall, it provides a secure, transparent, and efficient alternative to conventional voting systems, though scalability and implementation challenges remain.

2. Blockchain + RAG-Based Cosmetic Safety System (Summary)

This research proposes an AI-driven system that analyzes cosmetic ingredient safety using OCR, machine learning, and Retrieval-Augmented Generation (RAG). It converts product labels into readable ingredient insights and evaluates them based on skin type and scientific dermatology data. The system reduces hallucination in LLM outputs by grounding responses in verified knowledge bases and achieves high accuracy (97.3% grounding). It uses SBERT embeddings, ChromaDB, and a microservices architecture (React, Spring Boot, Flask). Unlike existing tools, it focuses on ingredient-level safety analysis instead of product-level recommendations, improving personalization and transparency. Key limitations include OCR errors, limited dataset coverage, and lack of clinical validation.

3. IoT-Based Industrial Safety System (Summary)

The text describes an IoT-enabled industrial safety system designed to detect fire, gas leaks, temperature changes, humidity variations, and electrical faults in real time. Sensors (MQ135, flame sensor, DHT11, current sensor) collect environmental data, which is processed by ESP32/Arduino and transmitted to the ESP RainMaker cloud platform. If hazards are detected, the system triggers alarms, sends mobile alerts, and automatically shuts down equipment using relays. The system supports real-time monitoring, predictive maintenance, and historical data analysis to improve safety and reduce industrial accidents. It provides a scalable, automated, and proactive safety solution compared to manual inspection systems.

4. Educational Data Mining (EDM) for Student Performance Prediction (Summary)

This study focuses on using machine learning in Educational Data Mining (EDM) to predict student academic performance and identify at-risk learners early. It collects data from academic records, behavior, demographics, and psychological factors, then applies preprocessing and ML models like Decision Trees, Random Forest, SVM, and regression techniques. The goal is to classify students, predict grades, and recommend interventions such as personalized learning and career guidance. Evaluation uses metrics like accuracy, F1-score, and RMSE. The system helps educators improve teaching strategies but raises ethical concerns about bias, privacy, and fairness. Future work includes real-time data integration, deep learning, and personalized career recommendation systems.

Conclusion

Machine learning has been proved to be effective in the early detection of children who are at risk, as indicated by the academic performance prediction model that has been recommended. This model comes from the field of machine learning. This enables educational institutions to shift away from reactive measures and toward proactive therapies, which, in turn, leads to a reduction in the number of students who drop out of school and brings about an increase in the overall academic outcomes. Consequently, academic outcomes are improved. For the purpose of developing capability-based and tailored education, the classification of slow and fast learners, which is based on deep learning, provides unique insights that can be employed. Regardless of the pace at which they are acquiring knowledge, each and every student is able to reap the benefits of this because it helps to enhance their level of engagement, knowledge, and overall performance. According to the career suggestion model, the integration of academic, psychometric, and interest-based data can result in the formulation of precise and individualized career advice that is delivered to the individual. This is an additional benefit of the model. With the support of this, students are able to make decisions that are founded on appropriate knowledge, which considerably improves the alignment of the workforce. Over the course of its whole, the study establishes a foundation for educational strategies that are capable of being intelligent, equitable, and data-driven. Students, educational institutions, and the community as a whole can all benefit from the implementation of these strategies.

References

[1] Dalia Khairy, Nouf Alharbi, Mohamed A. Amasha, Marwa F. Areed, Salem Alkhalaf, Rania A. Abougalala. (2024). Prediction of student exam performance using data mining classification algorithms. Education and Information Technologies, 29:21621–21645 [2] M. AArul Rozario, Dr. R. GunaSundari. (2024). Predicting and Analysis of Students’ Academic Performance using Hybrid Techniques. International Journal of Intelligent Systems and Applications in Engineering IJISAE, 12(3), 4189–4195 [3] Mohamed Bellaj, Ahmed Ben Dahmane, Said Boudra, Mohammed Lamarti Sefian. (2024). Educational Data Mining: Employing Machine Learning Techniques and Hyperparameter Optimization to Improve Students’ Academic Performance. International Journal of Online and Biomedical Engineering (iJOE)iJOE, Vol. 20 No. 3 [4] Esmael Ahmed. (2024). Student Performance Prediction Using Machine Learning Algorithms. Hindawi Applied Computational Intelligence and Soft Computing, Volume, Article ID 4067721 [5] Athanasios Angeioplastis, John Aliprantis, Markos Konstantakis, Alkiviadis Tsimpiris. (2025). Predicting Student Performance and Enhancing Learning Outcomes: A Data-Driven Approach Using Educational Data Mining Techniques. Computers, 14, 83 [6] Mehmooda, H., Khalid, A., Kostakos, P., Gilman, E., &Pirttikangas, S. (2024). A novel edge architecture and solution for detecting concept drift in smart environments. Future Generation Computer Systems, 150, 127–143. [7] Mahdia, O. A., Ali, N., Pardede, E., & Al-Quraishi, T. (2024). Online concept drift detector: Optimally balancing delay detection, runtime, memory, and accuracy. Procedia Computer Science, 237, 559–567. [8] Yawen Chen, Jiande Sun, Jinhui Wang, Liang Zhao, Xinmin Song, Linbo Zhai. (2025). Machine Learning-Driven Student Performance Prediction for Enhancing Tiered Instruction. arXiv:2502.03143v1 [cs.LG] 5 Feb. [9] Sazol Sarker, Mahit Kumar Paul, Sheikh Tasnimul Hasan Thasin, Md. Al Mehedi Hasan. (2024). Analyzing students’ academic performance using educational data mining. Computers and Education: Artificial Intelligence, 7, 100263 [10] Md. Mahmudul Islam, Farhad Hossain Sojib, Md. Fazle Hasan Mihad, Mahmudul Hasan, Mahfujur Rahman. (2025). The integration of explainable AI in Educational Data Mining for student academic performance prediction and support system. Telematics and Informatics Reports, Volume 18, June, 100203 [11] Ahmed Kord, Ahmed Aboelfetouh, Samaa M. Shohieb. (2025). Academic course planning recommendation and students’ performance prediction multimodal based on educational data mining techniques. Journal of Computing in Higher Education, Vol 2, 324 [12] Venera Nakhipova, Yerzhan Kerimbekov, Zhanat Umarova, Laura Suleimenova, Saule Botayeva, Almira Ibashova, and Nurlybek Zhumatayev. (2024). Use of the Naive Bayes Classifier Algorithm in Machine Learning for Student Performance Prediction. International Journal of Information and Education Technology, Vol. 14, No. 1. [13] Arash Khosravi, Ahmad Azarnik. (2024). Leveraging Educational Data Mining: XGBoost and Random Forest for Predicting Student Achievement. International Journal of Data Science and Advanced Analytics (ISSN: 2563-4429). [14] Munaf Salim Najim Al-Din and Hussein Ali Al Abdulqader. (2024). Students’ Academic Performance Prediction Using Educational Data Mining and Machine Learning: A Systematic Review.International Journal of Research and Innovation in Social Science (Ijriss) ISSN No. 2454-6186 | DOI: 10.47772/IJRISS |Volume VIII Issue VIII August, Page 1264 [15] Linqiang Tang, Chen Sian. (2025). Educational Data Mining For Student Performance Prediction. Scalable Computing: Practice and Experience, ISSN 1895-1767, SCPE. Volume 26, Issues 3, pp. 1551–1558 [16] Abdullah Al-Ameri, Aniello Castiglione, Michele Nappi, Chiara Pero, Muhammad Umer. (2024). Student Academic Success Prediction Using Learning Management Multimedia Data With Convoluted Features and Ensemble Model.ACM J. Data Inform. Quality, ACM 1936-1963/2024/8-ART [17] Bello, H. O., Ige, A. B., & Ameyaw, M. N. (2024). Adaptive machine learning models: Concepts for real-time financial fraud prevention in dynamic environments World Journal of Advanced Engineering Technology and Sciences, 12(2), 21–34. [18] Popoola, N. T. (2023). Big data-driven financial fraud detection and anomaly detection systems for regulatory compliance and market stability. International Journal of Computer Applications Technology and Research, 12(9), 32–46. https://doi.org/10.7753/IJCATR1209.1004 [19] Saleem Malik, S. Gopal Krishna Patro, Chandrakanta Mahanty, Rashmi Hegde, Quadri Noorulhasan Naveed, Ayodele Lasisi, Abdulrajak Buradi, Addisu Frinjo Emma, Naoufel Kraiem. (2025). Advancing educational data mining for enhanced student performance prediction: a fusion of feature selection algorithms and classification techniques with dynamic feature ensemble evolution. Scientific Reports, (2025) 15:8738 [20] Evelina Staneviciene, Daina Gudoniene, Vytenis Punys, Arturas Kukstys. (2024). A Case Study on the Data Mining-Based Prediction of Students’ Performance for Effective and Sustainable E-Learning. Sustainability, 16, 10442 [21] Jedidi Y., Ibriz A., Benslimane M., Hachmoud A., Tmimi M., Hajjioui Y., Rahhali M. (2024). Predicting students’ academic performance and modeling using data mining techniques. Mathematical ModelingAnd Computing, Vol. 11, No. 3, pp. 814–825 [22] Esmael Ahmed. (2024). Student Performance Prediction Using Machine Learning Algorithms. Applied Computational Intelligence and Soft Computing Volume, Article ID 4067721, 15 pages [23] Murnawan, Sri Lestari, Rosalim Samihardjo, DeshintaArrova Dewi. (2024). Sustainable Educational Data Mining Studies: Identifying Key Factors and Techniques for Predicting Student Academic Performance. Journal of Applied Data Sciences, Vol. 5, No. 3, September, pp. 1325-1342 ISSN 2723-6471 1325 [24] Furkan AYDIN. (2024). Prediction of Academic Success and Selection of Effective Features with Machine Learning. BUEFAD, Volume 14, Issue 1, 14(1), 181-195 [25] ?enay Kocakoyun Aydo?an, Turgut Pura, Fatih Bingül. (2024). Predicting Students\' Academic Performances Using Machine Learning Algorithms in Educational Data Mining. Malaysian Online Journal of Educational Technology, (Volume 12 - Issue 4 )

Copyright

Copyright © 2026 Prof. P. S. Ingle, Anand Laxminarayan Jaiswal, Raj Kailas Gore, Mohammad Sofiyan Md. Aijaz, Akshali Arun Parihar, Kajal Arun Jadhao. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.