Home

  Editors

  Ethics

  Submission

  Volumes

  Indexing

  Copyright

  Fees

  Subscription

  Publisher

  Support

  EPPM

 

Journal of Engineering, Project, and Production Management, 2026, 16(6), 2026-210

 

An Economic Forecasting Model Combining GA and Caputo Fractional Derivative

 

Haiyan Mi

Certified Teacher, School of Economics and Management, Yiwu Industrial & Commercial College, Yiwu 322000, China, E-mail: mihaiyann@outlook.com

 

Project Management

 

Received February 28, 2026; revised April 3, 2026; accepted June 19, 2026

 

Available online June 30, 2026

 

Abstract:   The economic system exhibits strong memory, path dependence, and nonlinear characteristics, and traditional integer-order models struggle to accurately characterize its long-range correlations and historical cumulative effects. Therefore, this study proposes an economic forecasting model that integrates a Genetic Algorithm (GA) and the Caputo Fractional Derivative (GA-Caputo), using quarterly Gross Domestic Product (GDP) data from China (2010-2023), to address the insufficient dynamic adaptability of fractional models and improve prediction accuracy and economic interpretability in complex environments. The results show that the Root Mean Square Error (RMSE) of the research model throughout the entire period is significantly lower than that of the control model during the epidemic period, and the prediction error during the epidemic period decreases by 22.8%-35.9%. The research model predicts an interval coverage rate of 94.2%, with the best performance and the narrowest interval width. The optimal order α is strongly correlated with the volatility of gross domestic product, verifying that a fractional order can dynamically reflect the strength of economic memory. The findings demonstrate that the GA-Caputo model addresses the limitations of traditional models in long-range dependency characterization and dynamic adaptability by synergistically optimizing fractional order structures and parameters, offering a robust framework for high-precision and highly interpretable economic forecasting.

 

Keywords:  Genetic algorithms; economic forecast; fractional order model; Gross Domestic Product (GDP); simulated annealing.

Copyright © Journal of Engineering, Project, and Production Management (EPPM-Journal).

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

Requests for reprints and permissions at eppm.journal@gmail.com.

Citation: Mi, H. (2026). An Economic Forecasting Model Combining GA and Caputo Fractional Derivative. Journal of Engineering, Project, and Production Management, 16(6), 2026-210.

DOI: 10.32738/JEPPM-2026-210

Full Text


Copyright © EPPM-Journal. All rights reserved.