College of Computer Science and Mathematics

Discussion of a higher diploma thesis in the College of Computer Science and Mathematics – Department of Statistics and Informatics entitled (Forecasting OPEC crude oil prices using conversion function models)
A higher diploma thesis was discussed at the College of Science and Computer at the University of Mosul on Sunday 10/4/2022 on forecasting crude oil prices for OPEC using transfer function models by the student Hashem Hussein Awad and under the supervision of the teacher Dr. Naglaa Saad Ibrahim
This study dealt with comparing the prediction accuracy of multivariate time series using Transfer Function Model models by dividing the study sample of the data into three samples of different sizes, estimating the transfer function model for each sample, and comparing the prediction accuracy between the three models.This study was applied to real data, and it was concluded that the predictive values ​​that were estimated according to the conversion function models for the three samples (a sample that includes complete data with a size of (n = 180) observations, a medium sample with a size of (n = 140) observations, and a small sample with a size of (n = 140) observations. (n=72) observations) were somewhat close to the original values, and the value of the mean standard errors for the three samples of data was negative, meaning that most errors are negative, which is evidence that the approved predictions give optimistic results. But when we compare the three models of the conversion function for the three samples in terms of prediction accuracy, we find that the data sample (n = 72) has the lowest values ​​for the prediction accuracy criteria (MSE, MAE), in addition to that the value of the ME standard is negative and very close to zero, as the higher the value Close to zero the prediction was better.The discussion committee was chaired by Assistant Professor Dr. Hiyam Abdel Majid Hayawi and the membership of Assistant Professor Dr. Raya Salem Muhammad Ali, and under the supervision and membership of the teacher, Dr. Naglaa Saad Ibrahim