Research on the Application of Machine Learning in the Asset Management Industry: A Literature Reviewof Risk Assessment and Investment Decision-Making

DOI: https://doi.org/10.62517/jse.202611208

Author(s)

Zhengtao Xu

Affiliation(s)

Civil Engineering (Leeds Joint School), Southwest Jiaotong University, Chengdu, Sichuan, China

Abstract

Against the backdrop where the digital economy accounts for 42.8% of GDP, coupled with policy support and growing technology investment, the asset management industry is transitioning from experience-driven to technology-driven. This paper focuses on the core scenarios of risk assessment and investment decision-making, sorts out three core machine learning algorithms (supervised learning, unsupervised learning, and reinforcement learning), and analyzes their application value in credit risk assessment, market risk assessment, intelligent portfolio construction, and market trend prediction. Combined with empirical cases, it examines the challenges at the data, technology, and industry levels and puts forward corresponding suggestions. The research shows that machine learning, with its capabilities of multi-source data fusion, nonlinear relationship capture, and dynamic optimization, significantly improves the accuracy and efficiency of asset management business, providing core impetus for the high-quality development of the industry.

Keywords

Machine Learning; Asset Management; Risk Assessment; Investment Decision-Making; Financial Technology; Data Fusion; Algorithm Optimization

References

[1] CAICT. Research Report on China's Digital Economy Development 2024[R]. 2024. [2] The State Council. New Generation Artificial Intelligence Development Plan[Z]. 2017. [3] Liu Chunhang. Artificial Intelligence, Big Data and Financial Risk Management[J]. Financial Regulation Research, 2025,(05):1-11. [4] Xu Yuncheng, Yang Yongqing, Wu Hengliang, et al. Research on Customer Asset Allocation Decision Preference Prediction Based on Machine Learning[J]. Financial Technology Research, 2021,(03):45-56. [5] Dong Bingjie. Bank Farmer Microcredit Investment Decision Model Based on Default Probability[D]. Dalian University of Technology, 2024. [6] Tu Yan, Jin Guanhao. Research on Banking Systemic Risk Early Warning Integrating Financial Sentiment Analysis [J]. Journal of the Central University of Finance and Economics, 2025(11):56-73. [7] Wang Zifeng, Chen Juanjuan, Wang Tengrui. Predicting the Efficiency of Newly Established Branches of Postal Savings Bank in the Context of Digital Finance: An Explainable Machine Learning Approach [J]. Postal Research, 2025(6):15-23. [8] Xu Bo, He Yijun, Wen Jiancheng, et al. A Review of Deep Reinforcement Learning Applications in Quantitative Trading for Financial Markets [J]. Journal of Intelligent Science and Technology, 2024, 6(04): 416-428. [9] Liu Bin, Xu Shun, Li Haoran, et al. Do Group Characteristics Aid in Predicting Corporate Debt Crises? Empirical Evidence Based on Explainable Machine Learning Models [J]. China Industrial Economics, 2025(7):174-192. [10] Wang Shouyang, Zhang Yi, Zhang Tingting, et al. Research on Intelligent Assessment of Farmer Credit Risk Based on Sample Optimisation and Explainable Machine Learning [J]. Agricultural Economic Issues, 2025(11): 62-84. [11] Cao Zeren, Li Di. Research on Financial Risk Prediction and Early Warning Mechanisms for Chinese Commercial Banks Based on Big Data [J]. Shanghai Economy, 2025(6):93-112. [12] Lu Nachuan. Research on Credit Default Risk Assessment Based on K-means-SMOTE and Improved Stacking Methods [D]. Yangzhou University, 2025. [13] Song Gaoyan, Deng Xin, Zong Jiafeng. The Impact of Green Bonds on Corporate Green Total Factor Productivity: Empirical Evidence Based on Multi-Period Double Difference and Dual Machine Learning [J]. Exploration of Financial Theory, 2025(6):42-53. [14] Wu Guowei, Shang Jin. The Cost Advantage of Green Bond Issuance and Its Determinants: Evidence from Machine Learning [J]. Bonds, 2025(10):28-34. [15] Lü Wanqing, Xiao Zhaofu. Synergistic Effects of Digital Green Finance Platforms on Pollution Reduction and Carbon Mitigation: Evidence from Dual Machine Learning Causal Inference [J]. Journal of Guizhou University of Finance and Economics, 2025 [16] Yang Zhihui, Li Dongcheng, Chen Yutian. Can Risk Preference Serve as a Forward-Looking Indicator of China's Financial Risk? — New Evidence from Cutting-Edge Machine Learning Methods [J]. Management World, 2025, (10): 21-37. [17] Cheng Shi, Xu Jie. Estimation of Hong Kong's Potential Growth Rate: A Machine Learning Approach[J]. Shanghai Finance, 2025(11):14-23. [18] Liu Lingjun, Chen Xiaoliang, Chen Yanbin. Re-evaluating Factors Influencing Monetary Policy Effectiveness: An Approach Based on Explainable Machine Learning Methods [J]. Journal of Quantitative Economics and Technical Economics, 2026, (01): 27-52. [19] Wu Yongxia. The Impact of Big Data Applications on the Financialisation of Real Economy Enterprises: A Causal Inference Approach Based on Dual Machine Learning [J]. Accounting Research, 2024, (02): 56-68. [20] Shang Ying, Wang Zhucun, Yin Chengyuan. Research on Fintech Empowering Bank Efficiency in the Context of New Quality Productive Forces: Causal Inference Based on Dual Machine Learning[J]. Statistics Theory and Practice, 2025(10):4-11. [21] Zhu Kang, Tang Yong. Data Element Utilisation and Corporate Financial Asset Allocation: Evidence from Machine Learning and Text Analysis [J]. Accounting Research, 2025(6):1-19. [22] Ouyang Ruihui, Li Wenjie. Research on Commercial Bank Data Asset Valuation Based on the Shapley Value Model [J]. Modern Financial Research, 2025(8):32-46.