Per Capita Gross Product Forecasting Problem Based on RWPSO Optimization Weighting Model

With the development of economic globalization, accurate forecasting of regional economic indicators has become increasingly important. This paper addresses the problem of forecasting the gross domestic product (GDP) per capita in a region by applying three models: the one-dimensional linear regression model, the ARIMA time series model, and an optimized weighted prediction model based on the stochastic inertia weight improvement particle swarm algorithm (RWPSO). The results indicate that the RWPSO optimization weighted forecasting model outperforms the other traditional models in terms of fitting accuracy (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>), mean absolute error (MAE), and root mean square error (RMSE), showing the highest forecasting accuracy. Sensitivity analysis further verified the robustness and reliability of the RWPSO model. The final prediction results show that the per capita GDP of the region is expected to be $84,799.98 in 2023, $89,207.69 in 2024, and $93,154.14 in 2025. The study concludes that the RWPSO optimization weighted prediction model has significant advantages in economic forecasting, providing a scientific basis for regional economic planning and policy-making, and aiding in the promotion of high-quality economic development in the region.