Makine Öğrenmesi Yöntemleri ile Öğrenci Akademik Başarısının Tahmin Edilmesi

Öz

Bu çalışmada, öğrencilerin akademik performanslarını etkileyen bireysel ve çevresel faktörler kullanılarak makine öğrenmesi tabanlı bir not tahmin modeli geliştirilmiştir. Çalışmada ders çalışma süresi, derslere devam oranı, uyku süresi, önceki akademik başarı, akran etkisi ve öğrenme güçlüğü gibi değişkenleri içeren 6607 örnekten oluşan bir veri seti kullanılmıştır. Doğrusal Regresyon, Karar Ağacı, K-En Yakın Komşu, Destek Vektör Makineleri, Rastgele Orman ve Gradient Boosting algoritmaları uygulamalı olarak karşılaştırılmıştır. Uygulanan modellerin hiperparametreleri GridSearch ve Optuna kullanılarak optimize edilmiştir. Uygulanan algoritmaların performansları MSE, RMSE, MAE, MAPE ve R² metrikleri ile değerlendirilmiştir. Deneysel sonuçlar, Doğrusal Regresyon ve SVM'in 0.99 R² ile en yüksek tahmin doğruluğuna sahip olduğunu göstermiştir. Elde edilen bulgular, makine öğrenmesi modellerinin öğrencilerin akademik performanslarının öngörülmesinde etkili olduğunu ve bireyselleştirilmiş eğitim stratejilerinin geliştirilmesine katkı sağlayabileceğini göstermektedir.

Anahtar Kelimeler

• Makine Öğrenmesi
• Öğrenci Başarısı
• Akademik Performans Tahmini

Prediction of Student Academic Achievement Using Machine Learning Methods

Öz

In this study, a machine learning-based grade prediction model was developed using individual and environmental factors that affect students' academic performance. The study utilized a dataset consisting of 6,607 examples, including variables such as study time, class attendance rate, sleep duration, previous academic achievement, peer influence, and learning difficulties. Linear Regression, Decision Tree, K-Nearest Neighbor, Support Vector Machines, Random Forest, and Gradient Boosting algorithms were compared in practice. The hyperparameters of the applied models were optimized using GridSearch and Optuna. The performance of the applied algorithms was evaluated using MSE, RMSE, MAE, MAPE, and R² metrics. The experimental results showed that Linear Regression and SVM had the highest prediction accuracy with an R² of 0.99. The findings indicate that machine learning models are effective in predicting students' academic performance and can contribute to the development of personalized education strategies.

Anahtar Kelimeler

• Machine Learning
• Student Achievement
• Academic Performance Prediction

Kaynakça

1. Bahçeci, F., & Gürol, M. (2016). The effect of individualized instruction system on the academic achievement scores of students. Education Research International, 2016(1), 7392125.
2. Jin, S. H., Im, K., Yoo, M., Roll, I., & Seo, K. (2023). Supporting students’ self-regulated learning in online learning using artificial intelligence applications. International Journal of Educational Technology in Higher Education, 20(1), 37.
3. Lee, D., Huh, Y., Lin, C. Y., Reigeluth, C. M., & Lee, E. (2021). Differences in personalized learning practice and technology use in high-and low-performing learner-centered schools in the United States. Educational Technology Research and Development, 69(2), 1221-1245.
4. Mulaudzi, I. C. (2023). Factors affecting students’ academic performance: a case study of the university context. Journal of Social Science for Policy Implications, 11(1), 18-26.
5. Sarker, I. H. (2021). Data science and analytics: an overview from data-driven smart computing, decision-making and applications perspective. SN Computer Science, 2(5), 377.
6. Suleiman, I. B., Okunade, O. A., Dada, E. G., & Ezeanya, U. C. (2024). Key factors influencing students’ academic performance. Journal of Electrical Systems and Information Technology, 11(1), 41.
7. Ezzaim, A., Dahbi, A., Haidine, A., & Aqqal, A. (2023). Enhancing academic outcomes through an adaptive learning framework utilizing a novel machine learning-based performance prediction method. Data and Metadata, 2, 164-164.
8. Wilson, A., & Anwar, M. R. (2024). The future of adaptive machine learning algorithms in high-dimensional data processing. International Transactions on Artificial Intelligence, 3(1), 97-107.

9. Tong, T., & Li, Z. (2025). Predicting learning achievement using ensemble learning with result explanation. PLoS One, 20(1), e0312124.
10. I. D. Shetty, D. Shetty, and S. Roundhal, “Student Performance Prediction,” 2019. [Online]. Available: www.ijcat.com
11. K. Kishor, R. Sharma, and M. Chhabra, Micro-Electronics and Telecommunication Engineering, vol. 373. in Lecture Notes in Networks and Systems, vol. 373. Singapore: Springer Nature Singapore, 2022. doi: 10.1007/978-981-16-8721-1.
12. M. Mohammadi, M. Dawodi, W. Tomohisa, and N. Ahmadi, IEEE ICAIIC 2019 : the 1st International Conference on Artificial Intelligence in Information and Communication : February 11 (Mon.) ~ 13 (Wed.), 2019, Okinawa, Japan. IEEE, 2019.
13. I. Patra, M. Jawarneh, R. Raj, and Meenakshi, “Machine Learning Techniques for Classification and Prediction of Students Academic Performance,” in Advancements in Science and Technology for Healthcare, Agriculture, and Environmental Sustainability, CRC Press, 2024, pp. 63–68. doi: 10.1201/9781032708348-12.
14. D. Alboaneen, M. Almelihi, R. Alsubaie, R. Alghamdi, L. Alshehri, and R. Alharthi, “Development of a Web-Based Prediction System for Students’ Academic Performance,” Data (Basel), vol. 7, no. 2, Feb. 2022, doi: 10.3390/data7020021.
15. E. Tjandra, S. S. Kusumawardani, and R. Ferdiana, “Student performance prediction in higher education: A comprehensive review,” in AIP Conference Proceedings, American Institute of Physics Inc., Apr. 2022. doi: 10.1063/5.0080187.
16. P. Mehta and N. L. Student, “Student Performance Predictor,” International Research Journal of Engineering and Technology, 2022, [Online]. Available: www.irjet.net
17. D. Ying and J. Ma, “Student Performance Prediction with Regression Approach and Data Generation,” Applied Sciences (Switzerland), vol. 14, no. 3, Feb. 2024, doi: 10.3390/app14031148.
18. E. Ahmed, “Student Performance Prediction Using Machine Learning Algorithms,” Applied Computational Intelligence and Soft Computing, vol. 2024, 2024, doi: 10.1155/2024/4067721.
19. G. Aydin, “Üniversite öğrencilerinin başarısını yordayan kişisel faktörler,” Egitim Arastirmalari - Eurasian Journal of Educational Research, vol. 2017, no. 69, pp. 93–112, 2017, doi: 10.14689/ejer.2017.69.6.
20. J. Dhilipan, N. Vijayalakshmi, S. Suriya, and A. Christopher, “Prediction of Students Performance using Machine learning,” IOP Conf Ser Mater Sci Eng, vol. 1055, no. 1, p. 012122, Feb. 2021, doi: 10.1088/1757-899x/1055/1/012122.
21. M. Yıldız And C. Börekci, “Predicting Academic Achievement with Machine Learning Algorithms,” Journal of Educational Technology and Online Learning, vol. 3, no. 3, pp. 372–392, Sep. 2020, doi: 10.31681/jetol.773206.
22. S. Hussain and M. Q. Khan, “Student-Performulator: Predicting Students’ Academic Performance at Secondary and Intermediate Level Using Machine Learning,” Annals of Data Science, vol. 10, no. 3, pp. 637–655, Jun. 2023, doi: 10.1007/s40745-021-00341-0.
23. A. S. Hashim, W. A. Awadh, and A. K. Hamoud, “Student Performance Prediction Model based on Supervised Machine Learning Algorithms,” in IOP Conference Series: Materials Science and Engineering, IOP Publishing Ltd, Nov. 2020. doi: 10.1088/1757-899X/928/3/032019.
24. S. G. Essa, T. Celik, and N. E. Human-Hendricks, “Personalized Adaptive Learning Technologies Based on Machine Learning Techniques to Identify Learning Styles: A Systematic Literature Review,” IEEE Access, vol. 11, pp. 48392–48409, 2023, doi: 10.1109/ACCESS.2023.3276439.
25. S. G. Essa, T. Celik, and N. E. Human-Hendricks, “Personalized Adaptive Learning Technologies Based on Machine Learning Techniques to Identify Learning Styles: A Systematic Literature Review,” IEEE Access, vol. 11, pp. 48392–48409, 2023, doi: 10.1109/ACCESS.2023.3276439.
26. Y. A. Alsariera, Y. Baashar, G. Alkawsi, A. Mustafa, A. A. Alkahtani, and N. Ali, “Assessment and Evaluation of Different Machine Learning Algorithms for Predicting Student Performance,” 2022, Hindawi Limited. doi: 10.1155/2022/4151487.
27. S. Prabpal and K. Nitiwatthana, “Enhancing Learning Style Identification through Advanced Machine Learning Techniques Text Analytics of Models and Applications in Personalized Education,” 2024.
28. J. L. Rastrollo-Guerrero, J. A. Gómez-Pulido, and A. Durán-Domínguez, “Analyzing and predicting students’ performance by means of machine learning: A review,” Feb. 01, 2020, MDPI AG. doi: 10.3390/app10031042.
29. N. Yanes, A. M. Mostafa, M. Ezz, and S. N. Almuayqil, “A machine learning-based recommender system for improving students learning experiences,” IEEE Access, vol. 8, pp. 201218–201235, 2020, doi: 10.1109/ACCESS.2020.3036336.
30. B. Schölkopf, “SVMs - A practical consequence of learning theory,” IEEE Intelligent Systems and Their Applications, vol. 13, no. 4, pp. 18–21, Jul. 1998, doi: 10.1109/5254.708428.
31. B. Kocarık Gacar And İ. Deveci Kocakoç, “Regresyon Analizleri Mi Karar Ağaçları Mı?,” Celal Bayar Üniversitesi Sosyal Bilimler Dergisi, pp. 251–260, Dec. 2020, doi: 10.18026/cbayarsos.796172.
32. B. Karabulut, G. Arslan, And H. M. Ünver, “A Weighted Similarity Measure For K-Nearest Neighbors Algorithm,” Celal Bayar Üniversitesi Fen Bilimleri Dergisi, vol. 15, no. 4, pp. 393–400, Dec. 2019, doi: 10.18466/cbayarfbe.618964.
33. S. Özdemir, “Potentıal Dıstrıbutıon Modellıng And Mappıng Usıng Random Forest Method: An Example Of Yukarıgökdere Dıstrıct,” Turkish Journal of Forestry | Türkiye Ormancılık Dergisi, pp. 51–56, Mar. 2018, doi: 10.18182/tjf.342504.
34. S. Kilic, “Linear regression analysis,” Journal of Mood Disorders, vol. 3, no. 2, p. 90, 2013, doi: 10.5455/jmood.20130624120840.
35. M. F. Adak, R. Kibar, And K. Ovaz, “Anomaly Detection with Gradient Boosting Regressor on HVAC Systems,” Journal of Polytechnic, Dec. 2023, doi: 10.2339/politeknik.1379049.
36. N. M. Shahani, X. Zheng, C. Liu, F. U. Hassan, and P. Li, “Developing an XGBoost Regression Model for Predicting Young’s Modulus of Intact Sedimentary Rocks for the Stability of Surface and Subsurface Structures,” Front Earth Sci (Lausanne), vol. 9, Oct. 2021, doi: 10.3389/feart.2021.761990.
37. T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)?,” Feb. 28, 2014. doi: 10.5194/gmdd-7-1525-2014.
38. S. Sakallioǧlu, S. Kaçiranlar, and F. Akdeniz, “Mean squared error comparisons of some biased regression estimators,” Commun Stat Theory Methods, vol. 30, no. 2, pp. 347–361, 2001, doi: 10.1081/STA-100002036.
39. Günel Alptekin, “Some Crıtıcs On The Use Of Coeffıcıent Of Determınatıon As A Sıgnıfıcance Test Crıterıon For Regressıon Equatıon ,” 2003.
40. S. Kim and H. Kim, “A new metric of absolute percentage error for intermittent demand forecasts,” Int J Forecast, vol. 32, no. 3, pp. 669–679, Jul. 2016, doi: 10.1016/j.ijforecast.2015.12.003.