Forecasting the Population of Türkiye Using Grey Models

Population forecasting plays a significant role in determining demography, eco0 nomics, and agriculture policies for developing countries. In this study, we employ the five different grey prediction models to estimate the population of Türkiye up to the year 2050. These models are given as the grey standard (GM (1,1)), grey time0varying dynamic (GM (1,1)t), grey Gompertz (GGM), grey Verhulst (GVM), and grey exponential (EXGM (1,1). The comparison of grey models is evaluated by mean absolute percentage error (MAPE), regression coefficient (R2), variance ratio (C), and probability of error (P). As a first application, we use a split for training (200702017) and testing (201802022) periods using from 2007 to 2022 address0based data. The EXGM (1,1) model demonstrates superiority in the analysis of training dataset. The GGM and GM (1,1)t models provide the most suitable results in the analysis of testing dataset. As a second application, we use the dataset for the period between 2007 and 2022. The GGM and GM (1,1)t were identified as the most appropriate models for predicting the 200702022 period. For the future population forecasts from 2023 to 2050, the results of the five models are compared with the projection values of the Turkish Statistical Institute published in 2018. The GGM is determined to be the most compatible based on the MAPE value of 0.68116 and the C value of 0.05218, and the Grey Verhulst model is provided with the most compatible R² value of 0.99818. According to the GGM, the population of Türkiye is projected to reach 105,948,975 up to the year 2050, 106,877,632 based on the GM (1,1) t, and 102,591,471 based on the GVM