Estimating the Number of Students in Najaf Governorate Education Using the LSTM Model and the ARIMA Model

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.