通过机器学习增强股票市场指数

IF 5.6 2区经济学 Q1 BUSINESS, FINANCE

Emerging Markets Review Pub Date : 2025-07-04 DOI:10.1016/j.ememar.2025.101325

Liangliang Zhang , Li Guo , Weiping Zhang , Tingting Ye , Qing Yang , Ruyan Tian

{"title":"通过机器学习增强股票市场指数","authors":"Liangliang Zhang , Li Guo , Weiping Zhang , Tingting Ye , Qing Yang , Ruyan Tian","doi":"10.1016/j.ememar.2025.101325","DOIUrl":null,"url":null,"abstract":"<div><div>Stock market index enhancement remains a widely adopted strategy among hedge funds within China’s financial market. The underlying algorithm aims to fine-tune the weightings of individual stocks within a benchmark index, thereby enhancing the performance of the target portfolio relative to its original benchmark.</div><div>Our innovative numerical framework stands out for its generality, rapidity, and theoretical convergence to the global optimum under reasonable assumptions. It also shines in tackling high-dimensional portfolio optimization problems. Empirical results demonstrate that the stock market index enhancement strategy, as computed by our algorithm, consistently delivers stable and significant excess returns, outperforming existing benchmarks.</div></div>","PeriodicalId":47886,"journal":{"name":"Emerging Markets Review","volume":"68 ","pages":"Article 101325"},"PeriodicalIF":5.6000,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Stock market index enhancement via machine learning\",\"authors\":\"Liangliang Zhang , Li Guo , Weiping Zhang , Tingting Ye , Qing Yang , Ruyan Tian\",\"doi\":\"10.1016/j.ememar.2025.101325\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Stock market index enhancement remains a widely adopted strategy among hedge funds within China’s financial market. The underlying algorithm aims to fine-tune the weightings of individual stocks within a benchmark index, thereby enhancing the performance of the target portfolio relative to its original benchmark.</div><div>Our innovative numerical framework stands out for its generality, rapidity, and theoretical convergence to the global optimum under reasonable assumptions. It also shines in tackling high-dimensional portfolio optimization problems. Empirical results demonstrate that the stock market index enhancement strategy, as computed by our algorithm, consistently delivers stable and significant excess returns, outperforming existing benchmarks.</div></div>\",\"PeriodicalId\":47886,\"journal\":{\"name\":\"Emerging Markets Review\",\"volume\":\"68 \",\"pages\":\"Article 101325\"},\"PeriodicalIF\":5.6000,\"publicationDate\":\"2025-07-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Emerging Markets Review\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1566014125000743\",\"RegionNum\":2,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BUSINESS, FINANCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Emerging Markets Review","FirstCategoryId":"96","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1566014125000743","RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}

引用次数: 0

摘要

中国金融市场上的对冲基金普遍采用股票市场指数提升策略。基础算法旨在微调基准指数中个股的权重，从而提高目标投资组合相对于原始基准的表现。我们创新的数值框架以其通用性，快速性和在合理假设下的理论收敛性而突出。它在处理高维投资组合优化问题方面也很出色。实证结果表明，本文算法计算的股票市场指数增强策略持续提供稳定且显著的超额回报，优于现有基准。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Stock market index enhancement via machine learning

Stock market index enhancement remains a widely adopted strategy among hedge funds within China’s financial market. The underlying algorithm aims to fine-tune the weightings of individual stocks within a benchmark index, thereby enhancing the performance of the target portfolio relative to its original benchmark.

Our innovative numerical framework stands out for its generality, rapidity, and theoretical convergence to the global optimum under reasonable assumptions. It also shines in tackling high-dimensional portfolio optimization problems. Empirical results demonstrate that the stock market index enhancement strategy, as computed by our algorithm, consistently delivers stable and significant excess returns, outperforming existing benchmarks.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Emerging Markets Review Multiple-

CiteScore

7.10

自引率

4.20%

发文量

审稿时长

100 days

期刊介绍： The intent of the editors is to consolidate Emerging Markets Review as the premier vehicle for publishing high impact empirical and theoretical studies in emerging markets finance. Preference will be given to comparative studies that take global and regional perspectives, detailed single country studies that address critical policy issues and have significant global and regional implications, and papers that address the interactions of national and international financial architecture. We especially welcome papers that take institutional as well as financial perspectives.