Öğrencilerin Akademik Performanslarının Tahmin Edilmesi için AutoML Tekniğinin Uygulanması

Year 2022, , 394 - 412, 31.05.2022

Sevda Aghalarova , Sinem Bozkurt Keser

https://doi.org/10.31202/ecjse.946505

Cited By: 2

Abstract

Eğitsel Veri Madenciliği, çeşitli eğitim kaynaklarından elde edilen büyük miktarda verinin analizini kolaylaştırmak amacıyla veri madenciliği yöntemlerinin geliştirilmesidir. Eğitimcilere geribildirimde bulunma, öğrencilere ders önerisinde bulunma, istenmeyen öğrenci davranışı belirleme, öğrenci performansını tahmin etme gibi konular Eğitsel Veri Madenciliği çalışma alanları arasında gösterilebilir. Doğru modeller oluşturularak bu alanlarda yapılacak iyileştirmeler ile eğitim kalitesi geliştirilebilir. Doğru modeller oluşturmak için uygun makine öğrenmesi algoritmalarının seçimi hem eğitimciler hem de veri bilimcileri için son derece önemlidir. Bu çalışmada öğrencilerin akademik performanslarını tahmin etmek amacıyla Otomatik Makine Öğrenmesi yöntemi ile çalışmada kullanılan veri kümesi için en iyi model araştırılmaktadır. Otomatik Makine Öğrenmesi ile veri önişleme, model seçimi ve hiper-parametre optimizasyonu gibi zorlu görevlerle uğraşmadan en iyi model bulunabilmektedir. Çalışmada, gerçek veri seti için Dağıtılmış Rastgele Orman algoritması en iyi algoritma olarak belirlenmektedir. Izgara araması kullanılarak algoritmanın hiper-parametreleri optimize edilmektedir. Deney sonuçlarında, Dağıtılmış Rastgele Orman algoritmasının, varsayılan hiper-parametreleri ile doğruluk ve f-skor değerleri sırasıyla %77.50 ve %80.01 olarak elde edilmektedir. Izgara araması ile bulunan optimal hiper-parametreler için doğruluk ve f-skor değerleri ise sırasıyla %82.30 ve %82.50 olarak hesaplanmaktadır.

Keywords

Eğitsel Veri Madenciliği, Makine Öğrenmesi, Öğrenci Akademik Performans Tahmini, Otomatik Makine Öğrenmesi.

Application of AutoML Technique for Predicting Academic Performance of Students

Abstract

Educational Data Mining is the development of data mining methods to facilitate the analysis of large amounts of data obtained from various educational sources. Issues such as providing feedback to educators, suggesting courses to students, identifying undesirable student behavior, and predicting the academic performance of students can be shown among the fields of Educational Data Mining. The quality of education can be improved with the improvements to be made in these areas by creating the right models. The selection of suitable machine learning algorithms to build accurate models is highly important for educators and data scientists. In this study, the best model for the dataset used in the study is investigated with the Automatic Machine Learning method in order to predict the students' academic performance. The best model can be found without dealing with difficult tasks such as data preprocessing, model selection, and hyper-parameter optimization using Automatic Machine Learning. In the study, the Distributed Random Forest algorithm is determined as the best algorithm for the real-world data set. And, the hyper-parameters of the algorithm are optimized using grid search. In the results of the experiments, the default hyper-parameters of the Distributed Random Forest algorithm and the accuracy and f-score values were obtained as 77.50% and 80.01%, respectively. For the optimal hyper-parameters found by grid search, the accuracy and f-score values are calculated as 82.30% and 82.50%, respectively.

Keywords

Educational Data Mining, Machine Learning, Prediction Student Academic Performance, AutoML.

References

• Ada, Ş., Başar, E., Dağlı, A., Ekinci, E., Ergün, M., Gelbal, S., Hoşgörür, V., Kıroğlu, K., Mahiroğlu, A., Taştan. N., ‘Eğitim bilimine giriş’, Pegem A Yayıncılık, Ankara, 2007.
• Tomasevic, N., Gvozdenovic, N., ve Vranes, S., ‘An overview and comparison of supervised data mining techniques for student exam performance prediction’, Computers & Education, 2020, 143: p, 103676.
• Baradwaj, B.K., ve S, Pal., ‘Mining educational data to analyze students' performance’, International Journal of Advanced Computer Science and Applications, 2011, 6(2).
• Romero, C., ve Ventura, S., ‘Educational data mining: a review of the state of the art’, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 2010, 40(6): p. 601-618.
• Pekuwali, A.A., ‘Prediction of student learning outcomes using the Naive Bayesian Algorithm’, (Case Study of Tama Jagakarsa University). in IOP Conference Series: Materials Science and Engineering, 2020, IOP Publishing.
• Shrestha, S., ve Pokharel, M., ‘Data Mining Applications Used in Education Sector’, Journal of Education and Research, 2020, 10(2), 27-51.
• Liñán, L.C., ve Pérez, Á.A.J., ‘Educational Data Mining and Learning Analytics: differences, similarities, and time evolution’, International Journal of Educational Technology in Higher Education, 2015, 12(3), 98-112.
• Gandy, R., Kasper, D., ve Luna, A., ‘Creating a Student Success Predictor Using Statistical Learning’, 2019.
• Ahammad, K., Chakraborty. B., Akter, E., Fomey, U.H., Rahman, S., ‘A Comparative Study of Different Machine Learning Techniques to Predict the Result of an Individual Student using Previous Performances’, International Journal of Computer Science and Information Security (IJCSIS), 2021, 19(1).
• Ghorbani, R., ve Ghousi, R., ‘Comparing different resampling methods in predicting Students’ performance using machine learning techniques’, IEEE Access, 2020, 8: p. 67899-67911.
• Singh, B.C., Protikuzzaman, M.D., Baowaly, M.K., Devnath, M.K., ‘Predicting Undergraduate Admission: A Case Study in Bangabandhu Sheikh Mujibur Rahman Science and Technology University, Bangladesh’, International Journal of Advanced Computer Science and Applications, 2020. 11.
• Wandera, H., Marivate, V., ve Sengeh, M.D., ‘Predicting school performance using a combination of traditional and non-traditional education data from South Africa’, 2019.
• Sagar, M., Gupta, A., ve Kaushal, R., ‘Performance prediction and behavioral analysis of student programming ability’, in 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2016, IEEE.
• Alshabandar, R., Hussain, A., Keight, R., Khan, W., ‘Students Performance Prediction in Online Courses Using Machine Learning Algorithms’, in 2020 International Joint Conference on Neural Networks (IJCNN), 2020, IEEE.
• Liu, W., XU, W., ZHAN, X., LIU, W., CHENG, W., ‘Student Performance Prediction by LMS Data and Classroom Videos’, in 2020 15th International Conference on Computer Science & Education (ICCSE), 2020, IEEE.
• Ha, D.T., Giap , C.N., Loan, P.H.T., Huong, N.T.L., ‘An Empirical Study for Student Academic Performance Prediction Using Machine Learning Techniques’, International Journal of Computer Science and Information Security (IJCSIS), 2020, 18(3).
• Asril, T., ve Isa, S.M., ‘Prediction of Students Study Period using K-Nearest Neighbor Algorithm’, International Journal, 2020, 8(6).
• Bunkar, K., ve Tanwani S., ‘Student Performance Prediction Using C4. 5 Decision Tree and CART Algorithm’, 2020, 2(9).
• Farissi, A., ve Dahlan, H.M., ‘Genetic Algorithm Based Feature Selection With Ensemble Methods For Student Academic Performance Prediction’ in Journal of Physics: Conference Series, 2020, IOP Publishing.
• Abbasoğlu, B., ‘Ortaokul Öğrencilerinin Akademik Başarılarının Eğitsel Veri Madenciliği Yöntemleri ile Tahmini’, Veri Bilimi, 2020, 3(1), 1-10.
• Sathe, M.T., ve Adamuthe, A.C., ‘Comparative Study of Supervised Algorithms for Prediction of Students' Performance’, International Journal of Modern Education & Computer Science, 2021, 13(1).
• Tsiakmaki, M., Kostopoulos, G., Kotsiantis, S., Ragos, O., ‘Implementing AutoML in educational data mining for prediction tasks’ Applied Sciences, 2020, 10(1): p. 90.
• Halvari, T., Nurminen, J.K., ve Mikkonen, T., ‘Testing the Robustness of AutoML Systems’, International Conference on Tools with Artificial Intelligence, 2020.
• He, X., Zhao, K., ve Chu, X., ‘AutoML: A Survey of the State-of-the-Art’, Knowledge-Based Systems, 2021, 212: p. 106622.
• LeDell, E., ve Poirier, S., ‘H2o automl: Scalable automatic machine learning’, in Proceedings of the AutoML Workshop at ICML, 2020.
• Truong, A., Walters, A., Goodsitt, J., Hines, K., Bruss, C.B., Farivar, R., ‘Towards automated machine learning: Evaluation and comparison of AutoML approaches and tools’, in 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 2019, IEEE.
• Zöller, M.A., ve Huber, M.F., ‘Benchmark and survey of automated machine learning frameworks’ Journal of Artificial Intelligence Research, 2021.
• Yao, Q., Wang, M., Chen, Y., Dai, W., Li, Y.F., Tu, W.W., Yang, Q., Yu, Y., ‘Taking human out of learning applications: A survey on automated machine learning’, 2018, arXiv preprint arXiv:1810.13306.
• Visa, S., Inoue, A., Ralescu, A., ‘Confusion Matrix-based Feature Selection’, MAICS, 2011, 710: p. 120-127.
• Lever, J., Krzywinski, M., ve Altman , N., ‘Classification evaluation’, 2016, Nature Publishing Group.
• Cortes, C., ve Mohri, M., ‘AUC optimization vs. error rate minimization’, Advances in neural information processing systems, 2003, 16: p. 313-320.
• Moisa, V., ‘Adaptive learning management system’, Journal of Mobile, Embedded and Distributed Systems, 2013, 5(2), 70-77.
• https://docs.h2o.ai/, Erişim tarihi 23.04.2021.