A Decision-Support Framework for Economic Growth Forecasting under Smart Finance: Integrating Dynamic GMM, Threshold Regression, and Machine Learning Optimization

Xiaoning Lan

doi:10.31081/dmame8220251585

Authors

Xiaoning Lan School of Economics and Management, Quzhou College of Technology, Quzhou, China

DOI:

https://doi.org/10.31081/dmame8220251585

Keywords:

Smart Finance; Econometric Model; Economic Growth Forecast; EM Algorithm; Lasso Regression

Abstract

Forecasting economic growth in the context of smart finance necessitates decision-support systems that can synthesise diverse, high-frequency, and nonlinear financial indicators. This research introduces a hybrid decision-support frame-work that integrates Dynamic System GMM, threshold re-gression, and a machine learning optimisation procedure em-ploying Lasso–EM algorithms, aiming to improve both the precision and interpretability of macroeconomic forecasts. Employing panel data from Chinese provinces spanning 2010 to 2023, the proposed model addresses endogeneity con-cerns, identifies structural thresholds within the smart fi-nance–growth relationship, and performs rigorous variable selection to enhance decision-making efficacy. Empirical results indicate that smart finance substantially fosters eco-nomic growth; however, its effects display nonlinear thresh-old behaviour contingent on the extent of digital infrastruc-ture and the capacity for financial innovation. The incorpora-tion of Lasso–EM optimisation further reinforces predictive robustness, mitigating overfitting and stabilising model per-formance. Consequently, the framework provides an ad-vanced tool for policymakers and economic planners, facili-tating evidence-based resource allocation, early detection of economic fluctuations, and the optimisation of fiscal and financial strategies within smart finance contexts. This study contributes to decision science by linking econometric ap-proaches with machine learning optimisation, offering a scal-able methodology for economic forecasting and policy de-sign in digitalised economies.

Downloads

Download data is not yet available.

References

[1] Amoh, J. K., Abdul-Mumuni, A., Nsor-Ambala, R., & Amenyitor, E. A. (2024). The corruption-foreign direct investment nexus in sub-Saharan Africa: Fresh evidence from a panel threshold regression approach. Journal of Financial Crime, 31(3), 681-697. https://doi.org/10.1108/JFC-05-2023-0119

[2] Barigozzi, M., & Luciani, M. (2024). Quasi maximum likelihood estimation and inference of large approximate dynamic factor models via the EM algorithm (Finance and Economics Discussion Series, Issue. https://doi.org/10.48550/arXiv.1910.03821

[3] Berman, J. (2018). ISM semiannual economic forecast looks at 2018 as a growth year. Logistics Management, 57(6), 12-13. https://www.scmr.com/article/ism_semiannual_economic_forecast_looks_at_2018_as_a_growth_year

[4] Fritz, M., Forstinger, S., Feng, Y., & Aykroyd, R. (2025). Forecasting economic growth by combining local linear and standard approaches. Journal of Applied Statistics, 52(7), 1342-1360. https://doi.org/10.1080/02664763.2024.2424920

[5] Gorelov, B. A., Kaloshina, M. N., & Dianova, E. V. (2024). Formation of a procedure to model forecast financial and economic indicators. Russian Engineering Research, 44(8), 1220-1224. https://doi.org/10.3103/S1068798X24701983

[6] Gossman, K. A., & Hayes, M. G. (2018). An investigation into the ability of the reverse yield gap to forecast inflation and economic growth in South Africa. South African Journal of Economic and Management Sciences, 21(1), 1-13. https://hdl.handle.net/10520/EJC-10eda0df09

[7] Gotovsky, A. V. (2025). Challenges to economic growth of the republic of Belarus in the new reality. Studies on Russian Economic Development, 36(1), 21-34. https://doi.org/10.1134/S1075700724700497

[8] Gunawan, A., Triansyah, F. A., Karlina, R., Yusuf, G., Dinantika, A. R., & Wahyudi, A. (2023). Econometric model of economic growth in Indonesia using dynamic panel data. Kontigensi: Jurnal Ilmiah Manajemen, 11(1), 208-213. https://doi.org/10.56457/jimk.v11i1.344

[9] Guo, X., Yang, Z., Wang, Y., Qu, Z., Lu, Y., Lou, Y., Chen, M., & Ren, X. (2025). Lasso regression with molecular descriptors predicts natural product adsorption onto graphene oxide-derived adsorbents. Materials Chemistry and Physics, 347, 131419. https://doi.org/10.1016/j.matchemphys.2025.131419

[10] Han, C., & Kim, H. (2024). Dynamic panel GMM estimators with improved finite sample properties using parametric restrictions for dimension reduction. In Advanced Studies in Theoretical and Applied Econometrics (pp. 125-146). https://doi.org/10.1007/978-3-031-48385-1_6

[11] Heinisch, K., & Lindner, A. (2019). For how long do IMF forecasts of world economic growth stay up-to-date? Applied Economics Letters, 26(3), 255-260. https://doi.org/10.1080/13504851.2018.1459035

[12] Istikomah, I., & Taufiqqurrachman, F. (2025). Agricultural GDP, agricultural labor and farmer exchange rate on poverty in Sumatra Island: A dynamic panel approach-GMM. Jambura Equilibrium Journal, 7(1), 33-45. https://doi.org/10.37479/jej.v7i1.27837

[13] Jabeur, S. B., Ballouk, H., Arfi, W. B., & Khalfaoui, R. (2022). Machine learning-based modeling of the environmental degradation, institutional quality, and economic growth. Environmental Modeling & Assessment, 27(6), 953-966. https://doi.org/10.1007/s10666-021-09807-0

[14] Jiang, F., Tanackov, I., Zhang, Q. S., & Tian, S. Q. (2023). Analyzing Price and Profit Dynamics in Free Trade Port Supply Chains: A Blockchain-Centric Approach Under Consumer Sensitivity. Journal of Intelligent Management Decision, 2(4), 202-214. https://doi.org/10.56578/jimd020405

[15] Le, P. N. M. (2025). Threshold of lending interest rate and macroeconomic indicators: Impact on investment by ownership in Vietnam. Challenges in Sustainability, 13(4), 493-507. https://doi.org/10.56578/cis130402

[16] Liu, Y. (2025). Revolutionizing supply chain finance with blockchain: A comprehensive analysis of smart contracts and beyond. International Conference on Mechatronics and Intelligent Control (ICMIC 2024), 782-799. https://doi.org/ 10.1117/12.3045051

[17] Maheu, J. M., Song, Y., & Yang, Q. (2020). Oil price shocks and economic growth: The volatility link. International Journal of Forecasting, 36(2), 570-587. https://doi.org/10.1016/j.ijforecast.2019.07.008

[18] Marfatia, H. (2023). The financial market's ability to forecast economic growth: information from sectoral movements. Journal of Economic Studies, 50(7), 1467-1484. https://doi.org/10.1108/JES-08-2022-0466

[19] Meena, K., Vadivel, A., Sardar, T. H., Kotiyal, A., & Kumar, U. (2025). Harnessing deep learning and time series models for accurate global solar radiation prediction. Procedia Computer Science, 259, 98-107. https://doi.org/10.1016/j.procs.2025.03.311

[20] Mensaklo, E., Chaiboonsri, C., Chokethaworn, K., & Sriboonchitta, S. (2024). Bayesian fixed-effects panel kink regression with unknown threshold. In Applications of Optimal Transport to Economics and Related Topics (pp. 369-383). https://doi.org/10.1007/978-3-031-67770-0_28

[21] Meriem, L., & Henchiri, J. E. (2024). The Influence of National Economic and Financial Systems on the Performance of Initial Coin Offerings. Journal of Corporate Governance, Insurance, and Risk Management, 11(2), 138-147. https://doi.org/10.56578/jcgirm110205

[22] Robusti, C. D. S., Avelar, A. B. A., Farina, M. C., & Gananca, C. A. (2025). Blockchain and smart contracts: transforming digital entrepreneurial finance and venture funding. Journal of Small Business and Enterprise Development, 32(3), 739-761. https://doi.org/10.1108/JSBED-12-2023-0584

[23] Said, R. (2024). Financial inclusion and environmental pollution in sub-Saharan Africa: Moderating effects of economic growth and renewable energy. Environmental Science and Pollution Research, 31(43), 55346-55360. https://doi.org/10.1007/s11356-024-34785-7

[24] Singh, R., Tiwary, K. S., Kumar, K., & Kumar, A. (2025). Empowering a sustainable future: blockchain’s role in economy, organizations, and finance towards smart circular economy. In Blockchain Technologies for Smart Circular Economy and Organisational Sustainability (pp. 271-283). https://doi.org/10.1007/978-3-031-89183-0_17

[25] Sun, Y., Hong, Y., & Wang, S. (2019). Out-of-sample forecasts of China's economic growth and inflation using rolling weighted least squares. Journal of Management Science and Engineering, 4(1), 1-11. https://doi.org/10.1016/j.jmse.2019.03.002

[26] Tian, S., Liu, Z., Liu, H., & Shi, F. (2024). Prediction of power system frequency stability following disturbance. International Conference on Energy, Electrical and Power Engineering, 1033-1039. https://doi.org/ 10.1109/CEEPE62022.2024.10586576

[27] Wang, F., & Wu, C. (2025). Prediction of digital economy scale based on error correction LMDI-SD method. Statistics and Decision, 41(4), 29-34.

[28] Xue, L. (2021). The application of blockchain technology in the financial field. International Conference on Forthcoming Networks and Sustainability in AIoT Era, 130-134. https://doi.org/10.1109/FoNeS-AIoT54873.2021.00036

[29] Yan, Y., Le, X., Yang, T., & Yu, H. (2024). Interpretable PCA and SVM-based leak detection algorithm for identifying water leakage using SAR-derived moisture content and InSAR closure phase. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 15136-15147. https://doi.org/10.1109/JSTARS.2024.3443127

[30] Yang, P. R. (2020). Using the yield curve to forecast economic growth. Journal of Forecasting, 39(7), 1057-1080. https://doi.org/10.1002/for.2676

[31] Yi, Y., Huang, D., & Wang, X. (2024). Nowcasting GDP with big macroeconomic data. China Economic Quarterly, 24(3), 843-860. https://doi.org/10.1080/09720073.2014.11891414

[32] Zhang, C., Wang, F., Zhou, D., Dong, Z., He, S., & Zhou, Z. (2025). A CNN-based fault diagnosis method of multi-function integrated RF system using frequency domain scanning with Lasso regression. Knowledge-Based Systems, 309, 112836. https://doi.org/10.1016/j.knosys.2024.112836

[33] Zhang, J., Zhang, D., & Zhao, X. (2023). Macroeconomic nowcasting method and empirical study based on improved Kalman filtering algorithm. Statistics and Decision, 39(13), 57-61.

[34] Zou, Z., & Zhong, X. (2024). A new very high-order finite-difference method for linear stability analysis. Journal of Computational Physics, 512, 113135. https://doi.org/10.1016/j.jcp.2024.113135