NARX_CNN: Hybrid Deep Learning Approach for Student’s Performance Prediction Using Time Series Data

被引：0

作者：

Saravanan Radhakrishnan ^{[1
]}

V. Vijayarajan ^{[2
]}

机构：

[1] Vellore Institute of Technology, Vellore Campus, Katpadi, Tamil Nadu, Vellore

来源：

SN Computer Science | / 6卷 / 5期

关键词：

Convolutional neural network (CNN); Exponential moving average (EMA); Non-linear autoregressive exogenous (NARX); Relative strength index (RSI); Triple exponential average (TRIX);

D O I：

10.1007/s42979-025-04047-5

中图分类号：

学科分类号：

摘要：

The student performance prediction is essential for understanding the progress rate of the students. It helps in course selection and designing future study plans based on the student's needs. It reduces the dropout rate due to inefficiency and provides ideas to select courses and study plans. This paper introduces the NARX_Convolutional Neural Network (NARX_CNN) model for early student performance prediction. Initially, the input data is collected and preprocessed using average filling method. Afterwards, time-specific features like Bollinger Bands %B (BOLL %B), Relative Strength Index (RSI), Triple Exponential Average (TRIX), Exponential Moving Average (EMA), Moving Average Envelope (MAE), and Money Flow Index (MFI) are extracted. Thereafter, feature selection is performed using recursive feature elimination. However, the early student performance prediction is done using the proposed NARX-CNN. Furthermore, NARX_CNN attained maximal values of Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared are about 0.223, 0.473, 0.143, and 0.435. The final prediction results indicate that the devised model improves the learning capability of the students thereby reducing the dropout rate of the students. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

引用

共 36 条

[1]

Chis M., Banerjee S., Hassanien A.E., Clustering time series data: an evolutionary approach, Found Comput Intell Data Min, 6, pp. 193-207, (2009)

[2]

Sun H., Yin C., Chen H., Qiao L., Ouyang Y., David B., A student’s performance prediction method based on neural collaborative filtering, IEEE International Conference on Engineering, pp. 1-8, (2019)

[3]

Liu D., Zhang Y., Zhang J., Li Q., Zhang C., Yin Y.U., Multiple features fusion attention mechanism enhanced deep knowledge tracing for student performance prediction, IEEE Access, 8, pp. 194894-194903, (2020)

[4]

Piech C., Bassen J., Huang J., Ganguli S., Sahami M., Guibas L.J., Sohl-Dickstein J., Deep knowledge tracing, Adv Neural Inf Process Syst, 28, (2015)

[5]

Liu T., Wang C., Chang L., Gu T., Predicting high-risk students using learning behavior, Mathematics, 10, 14, (2022)

[6]

Shou Z., Xie M., Mo J., Zhang H., Predicting student performance in online learning: a multidimensional time-series data analysis approach, Appl Sci, 14, 6, (2024)

[7]

Wang X., Yu X., Guo L., Liu F., Xu L., Student performance prediction with short-term sequential campus behaviors, Information, 11, 4, (2020)

[8]

Chen H.C., Prasetyo E., Tseng S.S., Putra K.T., Kusumawardani S.S., Weng C.E., Week-wise student performance early prediction in virtual learning environment using a deep explainable artificial intelligence, Appl Sci, 12, 4, (2022)

[9]

Kumar R., Kumar P., Kumar Y., Time series data prediction using IoT and machine learning technique, Proc Comput Sci, 167, pp. 373-381, (2020)

[10]

Hamsa H., Indiradevi S., Kizhakkethottam J.J., Student academic performance prediction model using decision tree and fuzzy genetic algorithm, Proc Technol, 25, pp. 326-332, (2016)

← 1 2 3 4 →