Estimating the Number of Students in Najaf Governorate Education Using the LSTM Model and the ARIMA Model
DOI:
https://doi.org/10.17605/ijnras.v3i3.2019Keywords:
LSTM model, ARIMA models, BIC standard, AIC standardAbstract
Estimating the number of students is important in educational planning and making the necessary administrative decisions. For these estimates to be accurate, appropriate models must be chosen in the estimation process. The LSTM and ARIMA models are important and commonly applied models in time series forecasting. In this study, these models were used to estimate the number of students in the Najaf Governorate secondary stage, and a comparison was made between these models. In building the ARIMA model, the stability of the series was initially confirmed, and the necessary differences were taken to achieve this stability. Then, a comparison was made between a group of ARIMA models using the BIC, MSE, and AIC criteria to choose the most accurate model in estimating the number of students, and the best model ARIMA (0,2,1) was determined. As for the LSTM model, this model was built using the R program, where the model was trained and evaluated using the study data. The results showed the superiority of the LSTM model in estimating the number of students compared to the ARIMA model.
References
A Predictive Model That Aligns Admission Offers with Student Enrollment Probability (Educ. Sci. 2023, 13(5), 440
Akaike , H. (1974) , "A new look at the statistical model Identification " , IEEE Transactions on Automatic Control , Vol.19 , No.6 , PP. 716-723 .
Al-Otaibi, Fawzi: 2003 "Using time series and neural networks in predicting indices" Master's thesis at Al-Ahsa Applied, Suez Canal University, Port Said, Egypt.
Al-Shawadfi, G. A. (2003). A comparison between neural network and Box-Jenkins Forecasting Techniques With Application to Real data. The Research Bulletin, Human Resources Development and Research Center, College of Business and Economics, King Saud University PO. Box.
Anderson , O.D. (1976) , " Time series analysis and forecasting " ,
Aston Zhang et al., translated by Alaa Ta'ima (2022) "Deep Learning" Part Two, Modern Deep Learning Techniques Cairo, Dar Al-Ma'rifah.
Autocorrelations in Autoregressive – Integrated Moving Average Time Series Analysis .
Azza Hazem Zaki, Al-Khayat, Basil Younis Dhnoon (2005), Iraqi Journal of Statistical Sciences, Volume 5, Issue 8, pp. 63-79, 17 pp.
B. Ujkani, D. Minkovska and L. Stoyanova, "A Machine Learning Approach for Predicting Student Enrollment in the University," 2021 International Scientific Conference Electronics (ET), Sozopol, Bulgaria, 2021, pp. 1-4
Baker, B. D. (2001). Can flexible non-linear modeling tell us anything new about educational productivity? Economics of Education Review, 20(1), 81-92.
Box , G. E. and Price , D. A. (1970) , " Distribution of Residual Autocorrelations in Autoregressive – Integrated Moving Average Time Series Models " , JASA , Vol.55 , No.332 , PP.1509-1525 .
Box , G. E. and Price , D. A. (1976) , " Distribution of Residual
Box G. , E. , P. , and Jenkins G. , M. , T. (1976) , " Time Series Analysis” Forecasting and Control " , San Francisco , Holden-Day , U.S.A.
Brock Well , P.J. and Davis , R.A. (1991) , " Time Series Theory and
Butter worths, London and Boston.
Chimmula, V. K. R., & Zhang, L. (2020). Time series forecasting of COVID-19 transmission in Canada using LSTM networks. Chaos, Solitons & Fractals, 135, 109864.
Faraway, J., & Chatfield, C. (1998). Time series forecasting with neural networks: a comparative study using the air line data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 47(2), 231-250.
Hanan Khadari Mahdi (2023) "Comparison of neural networks with long short-term memory and Box and Jenks models" Scientific Journal of Commercial Research Volume 49 Issue 2 Part One Page 517-542.
Ittihad Muhammad Arshan, Nabil Ahmed Al-Afari, Saba Muhammad Alwan (2020) "Predicting the number of students accepted at Ibb University for the years (2018-2022 AD) using Box-Jenkins models" (Arab Studies in Education and Psychology) Volume 128 Issue 128, Pages 109-129
Lili Mou , Zhi Jin(2018) “Tree-Based Convolutional Neural Networks: Principles and Applications” (SpringerBriefs in Computer Science) 1st ed. 2018 Edition Part of: SpringerBriefs in Computer Science (322 books).
Methods ", 2nd ed , Springer Verlag New York Inc , New York .
Nam, K., & Schaefer, T. (1995). Forecasting international airline passenger traffic using neural networks. The Logistics and Transportation Review, 31(3), 239-252.
Omran, N. F., Abd-el Ghany, S. F., Saleh, H., Ali, A. A., Gumaei, A., & Al-Rakhami, M. (2021). Applying deep learning methods on time-series data for forecasting COVID-19 in Egypt, Kuwait, and Saudi Arabia. Complexity, 2021.
Rahad Imad Saliwa, Dhafer Ramadan Matar (2019) "Comparison of prediction performance between some artificial neural networks and the (Box-Jenkins) methodology with application" Iraqi Journal of Statistical Sciences, Volume 16, Issue 1, Pages 51-76
Shamo, Khaled Dawood ("(1987 Using the time series method to predict the number of monthly deposits at Rafidain Bank", Master's thesis in Statistics, College of Administration and Economics, University of Baghdad.
Tian, Y., Luthra, I., & Zhang, X. (2020). Forecasting COVID-19 cases using Machine Learning models. MedRxiv. 2020 .07.02.20145474
Wei, W. W. S. (1990). Time series analysis: Univariate and multivariate methods. Journal of the American Statistical Association, 33(1), DOI:10.2307/2289741.
Yee, V. P. (1998). Regularized radial basis function networks: theory and applications to probability estimation, classification, and time series prediction. (PhD). McMaster University, , Hamilton, Ontar
