Regional Economic Data Extraction and Development Prediction Based on an Improved GWO Algorithm.

Area of Science:

• Economic modeling
• Machine learning applications
• Optimization algorithms

Background:

• Accurate regional economic development requires robust feature extraction and reliable trend prediction for effective policy-making.
• Existing methods face challenges in optimizing feature extraction accuracy and prediction reliability for complex economic data.

Purpose of the Study:

• To develop and validate an integrated model for enhanced feature extraction and development prediction of regional economic data.
• To improve the accuracy and reliability of economic forecasting for scientific policy formulation.

Main Methods:

• Integration of an improved grey wolf optimization algorithm, support vector machine (SVM), and generative adversarial network (GAN).
• Testing the optimization algorithm's convergence speed and adaptability on unimodal and multi-modal functions.
• Comparative analysis on a steel wire rope dataset for feature extraction and classification accuracy.
• Application to Anhui Province's economic data (2011-2022) for forecasting evaluation.

Main Results:

• The optimization algorithm exhibited superior convergence speed and adaptability compared to existing methods.
• Achieved a 98.75% recognition rate on the steel wire rope dataset, outperforming PCA-GWO-SVM by 1.25%.
• Demonstrated high efficiency in high-dimensional feature processing and classification.
• Economic forecasting for Anhui Province showed minimal absolute error (103) and a low error rate (0.005) from 2011-2020, indicating outstanding stability.

Conclusions:

• The proposed integrated model effectively captures regional economic data characteristics and enhances prediction accuracy.
• The model provides a reliable scientific basis for regional economic development decisions and policy formulation.
• The approach offers a promising solution for complex optimization and prediction tasks in economic analysis.