Forecasting Using a Hybrid Model (NNAR) for Industrial Employment and Industrial Imports in Syria: An Indicative Study for the Period 2022–2027

Abstract

This study aims to analyze the reality and trends of selected indicators of the Syrian industrial sector, represented by the number of workers in the industrial sector and the volume of industrial imports, during the period (2000–2021), and to test the efficiency of the Neural Network Autoregressive (NNAR) model in forecasting their future trends under conditions of short time series and structural instability. The study adopts a descriptive–analytical approach supported by quantitative analysis and statistical forecasting methods. Historical trends of the studied variables are analyzed, followed by the construction of an NNAR model to generate forecasted values for the period (2022–2027). The results show that industrial employment experienced a growth phase before 2011, followed by a sharp contraction and then a limited gradual recovery. Industrial imports were characterized by instability with a relative downward tendency in recent years. The findings indicate that the NNAR model shows acceptable forecasting efficiency, suggesting an upward trend in industrial employment in contrast to a downward trend in industrial imports during the forecasting period.