Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment

Qinni Jiang

doi:10.47297/taposatWSP2633-456902.20260705

PDF
导出
分享
收藏
专辑

Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment

7卷第5期

浏览量: 0 Downloads: 1

Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment
Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment
International Business College, Dongbei University of Finance and Economics, Dalian, Liaoning, 116025, China
2026年7卷第5期页码：8-13
网络首发：2026-07-15，

纸质出版：2026-05-30
DOI：10.47297/taposatWSP2633-456902.20260705
Accepted：

Scan QR Code

Qinni Jiang. (2026). Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment. 科技理论与实践（英文版）, 7(5), 8-13.

Jiang Qinni.Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment[J].Theory and Practice of Science and Technology,2026,07(05):8-13.
Qinni Jiang. (2026). Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment. 科技理论与实践（英文版）, 7(5), 8-13. DOI： 10.47297/taposatWSP2633-456902.20260705.

Jiang Qinni.Application of Reinforcement Learning in Macroeconomic Policy Risk Assessment[J].Theory and Practice of Science and Technology,2026,07(05):8-13. DOI： 10.47297/taposatWSP2633-456902.20260705.

摘要

Abstract

This study examines the potential of reinforcement learning (RL) for macroeconomic policy risk assessment and seeks to strengthen the scientific basis of policy formulation in complex

dynamic economic environments. An RL framework based on the Markov Decision Process (MDP) is constructed by incorporating macroeconomic indicators such as GDP growth

unemployment

fiscal expenditure

public debt

and foreign direct investment. The model simulates policy adjustments and learns adaptive strategies through repeated interaction with the environment. Using simulated data and China's macroeconomic data for 2022-2024

the model is evaluated through prediction accuracy

cumulative reward

and scenario simulations. The results show that RL can capture delayed policy effects and forecast economic responses under alternative policy regimes. The findings indicate that RL provides a robust

adaptive

and data-driven tool for assessing the risks and long-term impacts of macroeconomic policy choices.

关键词

Keywords

references

forecasting and sovereign risk assessment using deep learning techniques[J ] . arXiv preprint arXiv: 2301.09856 , 2023.

Martovytskyi v, Argunov v, Ruban i, Et Al. Developing a Risk Management Approach Based on Reinforcement Training in the Formation of an Investment Portfolio[J]. Eastern-European Journal of Enterprise Technologies, 2023, 122(3).

Cui Y, Yao F. Integrating deep learning and reinforcement learning for enhanced financial risk forecasting in supply chain management[J]. Journal of the Knowledge Economy, 2024: 1-20.

Ju C, Zhu Y. Reinforcement Learning-Based Model for Enterprise Financial Asset Risk Assessment and Intelligent Decision-Making[J]. Applied and Computational Engineering, 2024, 97: 181-186.

Singh V, Chen S S , Singhania M, et al. How are reinforcement learning and deep learning algorithms used for big data based decision making in financial industries–A review and research agenda[J]. International Journal of Information Management Data Insights, 2022, 2(2): 100094.

Mhlanga D. Financial inclusion in emerging economies: The application of machine learning and artificial intelligence in credit risk assessment[J]. International journal of financial studies, 2021, 9(3): 39.

Babenko V, Panchyshyn A, Zomchak L, et al. Classical machine learning methods in economics research: Macro and micro level example[J]. WSEAS Transactions on Business and Economics, 2021, 18(22): 209-217.

Ogawa E, Luo P. Macroeconomic effects of global policy and financial risks[J]. International Journal of Finance & Economics, 2024, 29(1): 177-205.

Forni M, Gambetti L, Maffei- Faccioli N, et al. The effects of monetary policy on macroeconomic risk[J]. European Economic Review, 2024, 167: 104789.

Vanhercke B, Verdun A. The European semester as goldilocks: Macroeconomic policy coordination and the recovery and resilience facility[J]. JCMS: Journal of Common Market Studies, 2022, 60(1): 204-223.

Hunjra AI, Azam M, Bruna MG, et al. Sustainable development: The impact of political risk, macroeconomic policy uncertainty and ethnic conflict[J]. International Review of Financial Analysis, 2022, 84: 102370.

Fernández-Villaverde J, Gillingham KT, Scheidegger S. Climate change through the lens of macroeconomic modeling[J ] . Annual Review of Economics, 2024, 17 .

Johnson D R. Integrated risk assessment and management methods are necessary for effective implementation of natural hazards policy[J]. Risk Analysis, 2021, 41(7): 1240-1247.

Simpson N P, Mach K J, Constable A, et al. A framework for complex climate change risk assessment[J]. One Earth, 2021, 4(4): 489-501.

Schrieks T, Botzen W J W, Wens M, et al. Integrating behavioral theories in agent-based models for agricultural drought risk assessments[J]. Frontiers in water, 2021, 3: 686329.

Shi J, Zhao D, Ren F, et al. Spatiotemporal variation of soil heavy metals in China: The pollution status and risk assessment[J]. Science of the Total Environment, 2023, 871: 161768.

Wang H, Liu X, Zhao C, et al. Spatial-temporal pattern analysis of landscape ecological risk assessment based on land use/land cover change in Baishuijiang National nature reserve in Gansu Province, China[J]. Ecological Indicators, 2021, 124: 107454.