This study explores deep learning models for automated student knowledge assessment. Using data from 1,480 STEM students, ANN, CNN, LSTM, and a hybrid CNN-LSTM were evaluated. The hybrid model achieved highest accuracy (94.7%), outperforming baselines. Results highlight the effectiveness of combining temporal and static features for adaptive learning systems and early intervention,

Deep learning, knowledge assessment, student performance prediction

Arnold, K. E., & Pistilli, M. D. (2012). Course signals at Purdue: Using learning analytics to increase student success. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (LAK '12), pp. 267–270. ACM. https://doi.org/10.1145/2330601.2330666

Boud, D., & Falchikov, N. (2006). Aligning assessment with long-term learning. Assessment & Evaluation in Higher Education, 31(4), 399–413. https://doi.org/10.1080/02602930600679050

Gureckis, T. M., & Markant, D. B. (2012). Self-directed learning: A cognitive and computational perspective. Perspectives on Psychological Science, 7(5), 464–481. https://doi.org/10.1177/1745691612454304

Hembree, R. (1988). Correlates, causes, effects, and treatment of test anxiety. Review of Educational Research, 58(1), 47–77. https://doi.org/10.3102/00346543058001047

Huang, S., Liu, Y., & Zhao, R. (2020). Student performance prediction using convolutional neural networks on LMS data. IEEE Access, 8, 112470–112481. https://doi.org/10.1109/ACCESS.2020.2996034

Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). arXiv:1412.6980