Analysis and Research on Cross Sectional Returns of Hedge Funds based on Machine Learning

Gaofeng Xu; Chencheng Li

doi:10.6981/FEM.202412_5(12).0015

Authors

Gaofeng Xu
Chencheng Li

DOI:

https://doi.org/10.6981/FEM.202412_5(12).0015

Keywords:

Fund Market; Machine Learning; Investment Strategies.

Abstract

With the rapid development of the domestic fund market, research on fund evaluation and screening continues in academia and industry. Currently, the commonly used method is to establish an evaluation model based on the return and risk characteristics of fund product performance, and use historical data regression to predict future fund performance. However, the reality of the financial system often exhibits more complex nonlinear characteristics, which poses significant challenges for fund evaluation modeling and prediction work. The emergence of machine learning methods and the rapid development of IT technology have provided a new turning point for people to solve such problems. Using economic theory as a prior and machine learning methods, we aim to uncover hidden insights from data in order to better understand the complex relationship between investor expectations and portfolio performance, and design and develop investment strategies that better meet investor needs.

Downloads

Download data is not yet available.

References

[1] Zou W .The Construction and Implementation Path of the Audit System for Quality Control in the Big Data Era[J].Proceedings of Business and Economic Studies, 2023, 6(6):111-115.

[2] Campos G D L , Gianola D .Genomic Prediction in the Big Data Era[J].American scientist, 2023(5):111.

[3] Zhang R , Yang Z , Liu X .Exploring Random Forest Modeling of Accounting Disclosure Quality and ESG Performance in the Face of Big Data Era[J].Applied Mathematics and Nonlinear Sciences, 2024, 9(1).DOI:10.2478/amns-2024-3273.

[4] Jan D P , Liesbeth T , Serge B ,et al.Validation of a machine learning algorithm to identify pulmonary vein isolation during ablation procedures for the treatment of atrial fibrillation: results of the PVISION study[J].Europace, 2024(5):5.DOI:10.1093/europace/euae116.

[5] Computing C M .Retracted: Traditional Ceramic Sculpture Feature Recognition Based on the Machine Learning Algorithm[J].Wireless Communications and Mobile Computing, 2023.DOI:10.11 55/2023/9812659.

[6] Colic N , Milosevic P , Dragovic I C M S .IBA-VNS: A Logic-Based Machine Learning Algorithm and Its Application in Surgery[J].mathematics, 2024, 12(7).

[7] Seo B K .Financial Market Crash and Phase Transition: Through Model-Free Framework with Machine Learning[J]. 2020.

[8] Goel T , Chawla T , Verma N .Machine Learning Approach for Financial Analysis of Multiple Stock Market Return[J]. 2020.

[9] Feng J , Liu X , He Q ,et al.No more free lunch: The increasing popularity of machine learning and financial market efficiency[J].Economic and Political Studies, 2024, 12(1):34-57.DOI:10.1080/ 20954816.2023.2230622.

[10] Miragaia D A M , Ferreira J J M ,Cédric T. Vieira.Efficiency of Non-profit Organisations: a DEA Analysis in Support of Strategic Decision-Making[J].Journal of the Knowledge Economy, 2024, 15(1):3239-3265.

[11] Song H H , Zamora D G , Martinez W L .Handling multi-granular hesitant information: A group decision-making method based on cross-efficiency with regret theory[J].Expert Systems with Application, 2023, 227(Oct.):120332.1-120332.14.

[12] Jin F , Cai Y , Zhou L .Multiplicative Consistency and DEA Cross-Efficiency-Driven Decision-Making Method with Fuzzy Preference Relations[J].International Journal of Fuzzy Systems, 2023.