ÖĞRENCİLERİN AKADEMİK NOT ORTALAMALARININ MAKİNE ÖĞRENMESİ YÖNTEMLERİ İLE TAHMİNİ

Yıl 2025, Sayı: 50, 886 - 910, 31.08.2025

Serkan Metin

https://doi.org/10.14520/adyusbd.1627396

Öz

Bu çalışma, öğrencilerin akademik not ortalamalarını tahmin etmek için farklı makine öğrenmesi yöntemlerini kullanmıştır. Çalışmada, Gradient Boosting Regressor (GBR), Random Forest Regressor, Feedforward Neural Networks (FFNNs), XGBoost ve diğer modeller uygulanmış ve performansları MAE, RMSE, MAPE ve R² gibi metriklerle değerlendirilmiştir. Random Forest modeli, %100 R² ile en yüksek doğruluğu sağlamış ve en düşük hata oranlarına ulaşmıştır. Diğer modeller arasında Gradient Boosting ve XGBoost da yüksek doğruluk oranlarıyla öne çıkmıştır. Araştırma, öğrencilerin günlük çalışma saatleri, sosyal ve fiziksel aktiviteler ile stres seviyeleri gibi değişkenlerin akademik başarı üzerindeki etkilerini analiz etmiştir. Günlük çalışma saatleri, %73'lük pozitif korelasyonla başarı üzerindeki en güçlü etkiye sahip faktör olarak belirlenmiştir. Stres seviyesinin başarıya ölçülü bir şekilde pozitif etkisi olduğu görülürken, fiziksel aktivitelerin başarıyı az da olsa olumsuz etkilediği tespit edilmiştir

Anahtar Kelimeler

Akademik başarı , Makine öğrenmesi , Regresyon analizi , Tahmin

PREDICTION OF STUDENTS' ACADEMIC GRADE POINT AVERAGES USING MACHINE LEARNING METHODS

Öz

This study utilized various machine learning methods to predict students' academic grade point averages. The models applied in the study included Gradient Boosting Regressor (GBR), Random Forest Regressor, Feedforward Neural Networks (FFNNs), XGBoost, among others, and their performances were evaluated using metrics such as MAE, RMSE, MAPE, and R². The Random Forest model achieved the highest accuracy with an R² of 100% and the lowest error rates. Among the other models, Gradient Boosting and XGBoost also demonstrated high accuracy levels. The research analyzed the impact of variables such as daily study hours, social and physical activities, and stress levels on academic success. Daily study hours were identified as the most influential factor, with a 73% positive correlation to academic performance. While stress levels showed a moderate positive effect on success, physical activities were found to have a slightly negative impact.

Anahtar Kelimeler

Academic achievement , Machine learning , Regression analysis , Prediction

Kaynakça

• Acem, Y., Arslantaş, K., Bişirici, M., & Erdoğan, K. (2024). Öğretmenlerin Eğitimde Yapay Zeka Kullanımına Yönelik Tutumlarının İncelenmesi. International Journal of New Trends in Education and Social Sciences, 1(2), 12-23 https://doi.org/10.5281/zenodo.11113077
• Adak, M.F., & Duralioğlu, Ö. (2023). Makine Öğrenmesi Yöntemleri Kullanılarak Öğrencilerin Kazanım Bilgileri ile Sınavlardaki Başarı Durumunun Tahmini. Zeki Sistemler Teori ve Uygulamaları Dergisi 6(1), 43-51 doi: 10.38016/jista.1183353
• Ahmad, Z., & Shahzadi, E. (2018). Prediction of students’ academic performance using artificial neural network. Bulletin of Education and Research, 40(3), 157–164.
• Ahmed, D. M., Abdulazeez, A. M., & Zeebaree, D. Q. (2021). Predicting university's studentsperformance based on machine learning techniques. IEEE International Conference onAutomatic Control & Intelligent Systems (I2CACIS). doi:10.1109/I2CACIS52118.2021.9495862
• Ashenafi, M. M., Riccardi, G., & Ronchetti, M. (2015). Predicting students' final exam scores from their courseactivities. Frontiers in Education Conference (Fie), 372–380. DOI: https://doi.org/10.1109/FIE.2015.7344081
• Batool, S., Rashid, J., Nisar, M.W., Kim, J., Kwon, H., & Hussain, A. (2023). Educational data mining to predict students’ academic performance: A survey study. Education and Information Technologies, 28(1), 905–971. https://doi.org/10.1007/s10639-022-11152-y
• Chen, X., Xie, H., & Hwang, G. J. (2020). A multi-perspective study on artificial intelligence in education: Grants, conferences, journals, software tools, institutions, and researchers. Computers & Education: Artificial Intelligence, 1, https://doi.org/10.1016/j.caeai.2020.100005
• Fernandes, E., Holanda, M., Victorino, M., Borges, V., Carvalho, R., & Erven, V.G. (2019). Educational data mining : Predictive analysis of academic performance of public school students in the capital of Brazil. Journal of Business Research, 335–343. https://doi.org/10.1016/j. jbusr
• Gök, M. (2017). Makine Öğrenmesi Yöntemleri İle Akademik Başarının Tahmin Edilmesi. Gazi Üniversitesi Fen Bilimleri Dergisi, 5(3): 139-148.
• Hussain, M.M., Akbar, S., Hassan, S.A., Aziz, M.W., & Urooj, F. (2024). Prediction of Student’s Academic Performance through Data Mining Approach. Journal of Informatics and Web Engineering, 3(1) https://doi.org/10.33093/jiwe.2024.3.1.16
• Kalyani, B. S., Harisha, D., Ramyakrishna, V., & Manne, S. (2020). Evaluation of students performance usingneural networks. Intelligent Computing, Information and Control Systems, Iciccs 2019 [J]. 1039:499–505. Martins, M.V., Tolledo, D., Machado, J., Baptista, L.M., & Realinho, V. (2021). Early prediction of student’s performance in higher education: A case study. Paper presented at the World Conference on Information Systems and Technologies, pp. 166–175. https://doi.org/10.1007/978-3-030-72657-7_16
• Okubo, F., Yamashita, T., Shimada, A., & Ogata, H. A. (2017). Neural network approach for students'performance prediction. Seventh International Learning Analytics & Knowledge Conference. 598–599. https://doi.org/10.1145/3027385.3029479
• Parkavi, R., Karthikeyan, P., Sujitha, S., & Abdullah, A.S. (2024). Enhancing Educational Assessment: Predicting and Visualizing Student Performance using EDA and Machine Learning Techniques. Journal of Engineering Education Transformations, 37, 240-245
• Pallathadka, H., Wenda, A., Ramirez-Asís, E., Asis-Lopez, M., Flores-Albornoz, J., & Phasinam, K. (2023). Classification and prediction of student performance data using various machine learning algorithms. Materials Today: Proceedings, 80, 3782–3785. https://doi.org/10.1016/j.matpr.2021.07.382
• Qu, S. J., Li, K., Wu, B., Zhang, S. H., & Wang, Y. C. (2019). Predicting student achievement based on temporallearning behavior in MOOCs. Appl. Sciences-Basel, 9(24). https://doi.org/10.3390/app9245539
• Ouyang, F., & Jiao, P. (2021). Artificial intelligence in education: The three paradigms. Computers and Education: Artificial Intelligence, 2, 100020. https://doi.org/10.1016/j.caeai.2021.100020
• Rastrollo-Guerrero, J., Gómez-Pulido, J.A., & Durán-Domínguez, A. (2020). Analyzing and predicting students’ performance by means of machine learning: A review. Applied Sciences, 10(3), 1–16. https://doi.org/10.3390/app10031042
• Rebai, S., Ben Yahia, F., & Essid, H. (2020). A graphically based machine learning approach to predict secondary schools performance in Tunisia. Socio-Economic Planning Sciences, https://doi.org/10.1016/j.seps.2019.06.009
• Rodríguez-Hernandez , C.F., Musso , M., Kyndt , E., & Cascallar E. (2021). Artificial neural networks in academic performance prediction: Systematic implementation and predictor evaluation. Computers and Education: Artificial Intelligence 2- 100018 https://doi.org/10.1016/j.caeai.2021.100018
• Salloum, S.A., Alshurideh, M., Elnagar, A., Shaalan, K., & Tolba, F.M. (2020). Mining in educational data: Review and future directions. Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020), 1153, 92–102. https://doi.org/10.1007/978-3-030-44289-7_9
• Sekeroglu, B., Abiyev, R., Ilhan, A., Arslan, M., & Idoko, J.B. (2021). Systematic Literature Review on Machine Learning and Student Performance Prediction: Critical Gaps and Possible Remedies. Applied Sciences, 11(22), 10907. https://doi.org/10.3390/app112210907
• Wang, G. H., Zhang, J., & Fu, G. S. (2018) Predicting student behaviors and performance in online learningusing decision tree. 2018 Seventh International Conference of Educational Innovation through Technology, 214–219. Doi: 10.1109/EITT.2018.00050
• Xu, W., Gao, C., & Yang, H. (2024). Research on Student Performance Prediction Based on Deep Learning. Research Square. https://doi.org/10.21203/rs.3.rs-4967448/v1
• Xu, X., Wang, J., Peng, H., & Wu, R. (2019). Prediction of academic performance associated with internet usage behaviors using machine learning algorithms. Computers in Human Behavior, 166–173. https://doi.org/10.1016/j.chb.2019.04.015
• Yagci, M. (2022). Educational data mining: Prediction of students’ academic performance using machine learning algorithms. Smart Learning Environments, 9(1), 11. z
• Yauri, R.A., Suru, H.U., Afrifa, J., & Moses, H.G. (2024). A Machine Learning Approach in Predicting Student’s Academic Performance Using Artificial Neural Network. Journal of Computational and Cognitive Engineering, 3(2) 203–212. https://doi.org/10.47852/bonviewJCCE3202470
• Zilyas, D., & Yılmaz, A. (2023). Makine Öğrenmesi Yöntemleri İle Eğitim Başarısının Tahmini Modeli. Dicle University Journal of Engineering, 14(3), 437-447 https://doi.org/10.24012/dumf.1322273