Design of a Regional Economic Forecasting Model Using Optimal Nonlinear Support Vector Machines

Area of Science:

• Economics
• Computer Science
• Data Science

Background:

• Accurate regional economic forecasting is crucial for policymakers.
• Machine learning models offer advanced solutions for time series prediction.
• Optimizing machine learning model parameters is essential for performance.

Purpose of the Study:

• To develop an optimized machine learning model for regional economic prediction.
• To identify the current economic status of a region using advanced forecasting.
• To enhance the accuracy of economic time series analysis.

Main Methods:

• Development of the quasioppositional cuckoo search algorithm with a nonlinear support vector machine (QOCSO-NLSVM).
• Utilizing the density-based clustering algorithm (DBSCAN) for state clustering based on economic and demographic features.
• Applying the nonlinear support vector machine (NLSVM) for time series prediction with QOCSA parameter optimization.

Main Results:

• The QOCSO-NLSVM technique demonstrated superior performance compared to existing methods.
• Achieved a minimal mean square error of 70.548 or greater.
• Obtained a low root mean square error (RMSE) of 8.399, indicating high prediction accuracy.

Conclusions:

• The QOCSO-NLSVM technique effectively predicts regional economic activity.
• The proposed method offers a significant advancement in economic forecasting accuracy.
• This approach provides valuable insights for regional economic status identification.