本周市场普跌，指增组合收益承压 分析师 缪铃凯 SAC 证书编号：S0160525060003 miaolk@ctsec.com 分析师 韩乾 SAC 证书编号：S0160525060004 hanqian@ctsec.com 分析师 张淼 SAC 证书编号：S0160525080008 zhangmiao@ctsec.com 相关报告 1. 《沪深 300 增强超额收益领先市场》 2025-11-15 2. 《红利微盘哑铃型策略回归，指增超额表 现回暖》 2025-11-08 3. 《2025 年 12 月核心宽基指数成分股调 整预测》 2025-11-06 证券研究报告 量化选股策略周报/ 2025.11.22 核心观点 ❖ 我们基于深度学习框架构建 alpha 和风险模型，打造 AI 体系下的低 频指数增强策略： ❖ 风险提示：因子失效风险，模型失效风险，市场风格变动风险。 请阅读最后一页的重要声明！ ❖ 本周市场指数表现：截至 2025-11-21，本周上证指数下跌 3.90%，深证 成指下跌 5.13%，沪深 300 下跌 3.77%，市场情绪下降指数蒙受较大跌幅。 ❖ 本周指数增强基金表现：截至 ...

Core Viewpoint - The article discusses the shift in investment strategies among private equity investors, highlighting a growing interest in dividend stocks as a safer investment option amidst market uncertainties [3][5][11]. Group 1: Market Sentiment and Investment Strategies - There is a noticeable shift from the initial enthusiasm for quantitative strategies to a more rational approach, with investors seeking more certainty in their investments [3]. - Concerns about market beta and the potential for high valuations in small-cap stocks have led to a preference for dividend-paying stocks [4][5]. - The Shanghai Composite Index faces a resistance level at 4000 points, prompting cautious behavior among investors as year-end approaches [4]. Group 2: Dividend Stocks as a Safe Haven - Dividend stocks are viewed as a natural hedge due to their higher dividend yields, providing stable cash flow and a safety net for investors [5]. - Companies that offer stable high dividends typically have lower valuations and stable cash flows, making them more resilient during market downturns [5][6]. - Historical trends show that during market volatility, funds tend to flow into dividend stocks as a defensive strategy [5][8]. Group 3: Portfolio Diversification and Risk Management - Dividend stocks can effectively hedge against aggressive investment styles, particularly those concentrated in small-cap stocks [6][11]. - The current market environment suggests an acceleration in sector rotation, which may further enhance the appeal of dividend stocks [8]. - Investors are increasingly adopting a "barbell" strategy, combining small-cap holdings with dividend strategies to balance their portfolios [8]. Group 4: Future Outlook for Dividend Stocks - The A-share premium for traditional dividend sectors is expected to rise, with the market anticipating a recovery in the AH premium index [10]. - Policies aimed at reducing competition and optimizing supply structures are likely to benefit high-dividend traditional industry leaders [10]. - Long-term confidence in A-shares is growing, with a focus on reducing volatility in investment returns [11].

Core Insights - The report suggests increasing allocation to large-cap value stocks while focusing on TMT (Technology, Media, and Telecommunications) and cyclical sectors [3][30] - The industry rotation model has been optimized to adapt to market conditions, incorporating high-frequency factors and enhancing the strategy's effectiveness [4][26] - The latest industry rotation model identifies non-bank financials, steel, media, non-ferrous metals, environmental protection, and telecommunications as preferred sectors [30][33] Market Review and Fund Flow Tracking - As of October 31, 2025, the total monthly trading volume of A-shares reached 36.78 trillion yuan, with a slight decrease in daily average trading volume by 10.49% compared to the previous month [12][18] - The average stock return dispersion for the past month was 2.41%, indicating a slight decline but remaining above the median level for the past six months [12][18] - The industry rotation speed has continued to expand, significantly exceeding the average level since 2015 [12][18] Industry Rotation Model and ETF Fund Configuration - The report emphasizes the importance of focusing on large-cap value and cyclical sectors, particularly in the context of the current unclear market leadership [3][30] - The recommended ETF portfolio includes six funds: E Fund CSI 300 Non-Bank ETF, Guotai Junan CSI Steel ETF, GF CSI Media ETF, Southern CSI Non-Ferrous Metals ETF, Southern Yangtze River Protection Theme ETF, and Guotai Junan CSI All-Share Communication Equipment ETF [3][34] - The model's historical performance has shown consistent positive excess returns, outperforming major benchmark indices [5][42] Historical Performance and Model Effectiveness - The industry rotation model has maintained a strong performance over the years, achieving excess returns compared to industry averages, with a notable performance in 2025 [5][42] - The model's win rates over the past 1, 3, and 5 years are 83.33%, 69.44%, and 71.67% respectively, indicating its robustness [43][44] - The report highlights the significance of emotional and price-volume factors in capturing market dynamics, especially in weak market conditions [42][43]

Core Insights - The report emphasizes the construction of an AI-driven low-frequency index enhancement strategy using deep learning frameworks to build alpha and risk models [3] - The performance of major market indices shows positive trends, with the Shanghai Composite Index rising by 1.08% and the Shenzhen Component Index by 0.19% as of November 7, 2025 [5][8] - Year-to-date performance indicates that the CSI 300 Index has increased by 18.9%, while the CSI 300 enhanced portfolio has outperformed with a rise of 28.4%, yielding an excess return of 9.5% [19] Market Index Performance - As of November 7, 2025, the CSI 500 Index has seen a year-to-date increase of 28.0%, with its enhanced portfolio rising by 35.3%, resulting in an excess return of 7.3% [24] - The CSI 1000 Index has increased by 26.6% year-to-date, while its enhanced portfolio has risen by 40.9%, achieving an excess return of 14.4% [30] - The report highlights that sectors such as electric equipment, coal, and oil & petrochemicals performed well, with weekly returns of 4.98%, 4.52%, and 4.47% respectively [9][10] Index Enhancement Fund Performance - The CSI 300 enhanced fund reported a minimum excess return of -1.49%, a median of -0.22%, and a maximum of 0.84% for the week ending November 7, 2025 [11] - The CSI 500 enhanced fund had a minimum excess return of -1.05%, a median of 0.04%, and a maximum of 1.43% for the same period [11] - The CSI 1000 enhanced fund showed a minimum excess return of -1.69%, a median of -0.32%, and a maximum of 0.92% [11] Tracking Portfolio Performance - The report details that the AI-driven strategy involves weekly rebalancing with a maximum turnover rate of 10%, optimizing the combination of deep learning alpha signals and risk signals [15] - The CSI 300 enhanced portfolio has achieved a year-to-date return of 28.4%, significantly outperforming the CSI 300 index's 18.9% increase [19] - Historical performance data indicates that the CSI 500 enhanced portfolio has consistently outperformed its benchmark, with a year-to-date return of 35.3% compared to the CSI 500's 28.0% [25]

Core Insights - The report highlights the construction of an AI-based low-frequency index enhancement strategy using deep learning frameworks to build alpha and risk models [4][16] - The market indices showed positive performance as of October 24, 2025, with the Shanghai Composite Index rising by 2.88%, the Shenzhen Component Index by 4.73%, and the CSI 300 by 3.24%, indicating a market uptrend despite reduced trading volume [6][9][10] Market Index Performance - As of October 24, 2025, the Shanghai Composite Index reached 3950.3 points, with a weekly increase of 2.88% and a year-to-date increase of 17.86% [10] - The Shenzhen Component Index stood at 13289.2 points, increasing by 4.73% weekly and 27.60% year-to-date [10] - The CSI 300 Index was at 4660.7 points, with a weekly rise of 3.24% and a year-to-date increase of 18.44% [10] Index Enhancement Fund Performance - As of October 24, 2025, the CSI 300 index enhancement fund had a minimum excess return of -1.29%, a median of -0.08%, and a maximum of 1.86% for the week [13] - The CSI 500 index enhancement fund reported a minimum excess return of -1.78%, a median of 0.02%, and a maximum of 1.07% [13] - The CSI 1000 index enhancement fund had a minimum excess return of -1.39%, a median of 0.29%, and a maximum of 1.36% [13] Year-to-Date Performance of Index Enhancement Funds - The CSI 300 index enhancement fund has achieved a year-to-date excess return of 8.1%, with a total return of 26.5% compared to the CSI 300's 18.4% [20] - The CSI 500 index enhancement fund has recorded a year-to-date excess return of 6.4%, with a total return of 33.2% against the CSI 500's 26.8% [24] - The CSI 1000 index enhancement fund has shown a year-to-date excess return of 13.8%, with a total return of 38.3% compared to the CSI 1000's 24.5% [31] Tracking Portfolio Performance - The report emphasizes the use of deep learning frameworks to construct the CSI 300, CSI 500, and CSI 1000 index enhancement portfolios, optimizing alpha signals and risk signals through a combination of multi-source features and neural networks [16][21][25][29] - The CSI 300 index enhancement portfolio has shown a total return of 26.5% year-to-date, outperforming the CSI 300 index by 8.1% [20] - The CSI 500 index enhancement portfolio has achieved a total return of 33.2% year-to-date, with an excess return of 6.4% [24] - The CSI 1000 index enhancement portfolio has recorded a total return of 38.3% year-to-date, with an excess return of 13.8% [31]

- The report includes multiple quantitative models for market timing, such as the "Volume Model," "Low Volatility Model," "Feature Institutional Model," "Feature Volume Model," "Smart Algorithm Model," "Limit-Up-Limit-Down Model," "Calendar Effect Model," "Long-Term Momentum Model," and composite models like "A-Share Comprehensive Weapon V3 Model" and "A-Share Comprehensive Guozheng 2000 Model" [2][11][12][13][14] - The "Volume Model" is neutral in the short term, while the "Feature Volume Model" indicates bearish signals. The "Smart Algorithm Model" for CSI 500 also shows bearish signals, whereas the "Long-Term Momentum Model" is bullish for long-term market trends [11][13][14] - The "Composite Weapon V3 Model" and "Comprehensive Guozheng 2000 Model" both indicate bearish signals for A-shares, suggesting a negative outlook for the market [14][68] - For Hong Kong stocks, the "Turnover Inverse Volatility Model" continues to show bearish signals, indicating a negative outlook for the Hang Seng Index [15][63] - Backtesting results for the "Double Bottom Pattern" show a weekly decline of -2.06%, outperforming the Shanghai Composite Index by 1.37%. Since December 31, 2020, the cumulative return of the double bottom portfolio is 28.91%, compared to the Shanghai Composite Index's cumulative return of 10.04%, achieving an excess return of 18.88% [41][46] - Backtesting results for the "Cup-and-Handle Pattern" show a weekly decline of -5.45%, underperforming the Shanghai Composite Index by -2.02%. Since December 31, 2020, the cumulative return of the cup-and-handle portfolio is 62.41%, compared to the Shanghai Composite Index's cumulative return of 10.04%, achieving an excess return of 52.38% [41][42]

Core Insights - The report highlights a rebound in excess returns for index-enhanced strategies, indicating a positive shift in market performance [1] - The analysis is based on a deep learning framework that constructs alpha and risk models to create low-frequency index-enhanced strategies [4] Market Index Performance - As of September 26, 2025, the Shanghai Composite Index rose by 0.21%, the Shenzhen Component Index increased by 1.06%, and the CSI 300 Index gained 1.07%, with the STAR 50 showing strong performance [6][9] - The performance of index-enhanced funds for the week ending September 26, 2025, showed the CSI 300 index-enhanced fund had an excess return ranging from -1.59% to 0.86%, while the CSI 500 and CSI 1000 index-enhanced funds had similar ranges [6][14] Index Enhanced Fund Performance - Year-to-date, the CSI 300 index has increased by 15.6%, while the CSI 300 index-enhanced portfolio has risen by 22.8%, resulting in an excess return of 7.2% [6][22] - The CSI 500 index has seen a year-to-date increase of 26.5%, with its enhanced portfolio rising by 29.8%, yielding an excess return of 3.3% [6][27] - The CSI 1000 index has increased by 24.2% year-to-date, while its enhanced portfolio has risen by 35.1%, resulting in an excess return of 10.9% [6][33] Tracking Portfolio Performance - The report emphasizes the construction of index-enhanced portfolios for the CSI 300, CSI 500, and CSI 1000 using a deep learning framework, which optimizes alpha signals and risk signals [18] - The CSI 300 index-enhanced portfolio has shown a year-to-date return of 22.8%, outperforming the index itself [22][23] - The CSI 500 index-enhanced portfolio has achieved a year-to-date return of 29.8%, while the CSI 1000 index-enhanced portfolio has returned 35.1% [27][33]

Core Insights - The report highlights that the market indices have shown positive performance, with the Shanghai Composite Index rising by 1.70% and the Shenzhen Component Index increasing by 4.55% as of August 15, 2025, marking a new high since 2022 [5][8] - The report emphasizes the construction of an AI-based low-frequency index enhancement strategy using deep learning frameworks, which has resulted in significant outperformance of enhanced index portfolios compared to their respective benchmarks [5][13] Market Index Performance - As of August 15, 2025, the Shanghai Composite Index increased by 1.70%, the Shenzhen Component Index by 4.55%, and the CSI 300 Index by 2.37%, with the Shanghai Composite Index reaching a new high since 2022 [5][9] - Year-to-date performance shows the CSI 300 Index up by 6.8%, while the CSI 300 enhanced portfolio has risen by 17.1%, yielding an excess return of 10.3% [5][17] - The CSI 500 Index has increased by 14.7% year-to-date, with its enhanced portfolio up by 21.6%, resulting in an excess return of 6.9% [5][22] - The CSI 1000 Index has seen a year-to-date increase of 19.5%, with its enhanced portfolio rising by 29.4%, leading to an excess return of 9.9% [5][29] Enhanced Portfolio Performance - The report details the performance of the CSI 300 enhanced portfolio, which has achieved a return of 17.1% year-to-date compared to the CSI 300's 6.8% [17][18] - The CSI 500 enhanced portfolio has delivered a year-to-date return of 21.6%, outperforming the CSI 500's 14.7% [22][23] - The CSI 1000 enhanced portfolio has recorded a year-to-date return of 29.4%, significantly higher than the CSI 1000's 19.5% [29][30] Sector Performance - The report notes that the telecommunications, electronics, and non-bank financial sectors performed well this week, with weekly returns of 7.66%, 7.02%, and 6.48% respectively [9][10] - Conversely, the banking, steel, and textile sectors underperformed, with weekly returns of -3.19%, -2.04%, and -1.37% respectively [9][10]

Core Viewpoint - Niche strategy funds are gaining recognition and success in the market by avoiding mainstream competition and focusing on unique investment approaches, leading to significant performance and growth in assets under management [1][3][5]. Group 1: Performance of Niche Strategy Funds - Niche strategy funds have achieved substantial returns, with some funds maintaining positive returns for five consecutive years, such as 华夏新锦绣 and 金元顺安元启, which reported returns of 40.5% and 29.41% respectively this year [3][4]. - The 华夏新锦绣 fund, managed by 张城源, has accumulated a total return of 131.58% over five years, primarily utilizing a定增 strategy [3]. - The 金元顺安元启 fund, managed by 缪玮彬, has achieved a remarkable 262.3% return over five years, showcasing the effectiveness of the micro-cap stock strategy [4]. Group 2: Strategies Employed - Niche strategy funds employ various strategies such as定增, quantitative stock selection, micro-cap stock strategies, and tracking Smart Beta indices to uncover excess returns in overlooked market segments [3][4]. - The 国金量化多策略 fund, managed by 姚加红 and 马芳, has consistently achieved positive returns since 2019, with a return of 16.69% this year, demonstrating the broad sources of excess returns from its quantitative approach [4]. Group 3: Market Dynamics and Company Strategies - Smaller fund companies are leveraging their flexibility to quickly adapt and implement niche strategies, resulting in significant growth in assets under management, as seen with 国金基金, which grew from under 30 billion to nearly 130 billion [6]. - Larger fund companies, such as 华泰柏瑞, have also successfully launched niche products like the 红利低波ETF, which has grown from 2.58 billion to 221.4 billion in assets, benefiting from strong performance and market interest [7]. Group 4: Challenges Faced by Niche Strategy Funds - Despite their success, niche strategy funds face challenges such as the "scale trap," where initial performance pressures can lead to significant fluctuations in fund size, risking the viability of the strategy [9][10]. - The effectiveness of niche strategies often relies on specific market conditions or policies, making them vulnerable to changes in the market environment [10].

Core Viewpoint - Niche strategy funds are gaining recognition in the public fund industry, successfully breaking through traditional competition by exploring overlooked areas for excess returns [1][4][12]. Group 1: Performance of Niche Strategy Funds - The equity market has rebounded this year, leading to significant performance improvements for equity funds, particularly in mainstream sectors like technology and healthcare [3]. - Several niche strategy funds have achieved consistent positive returns over the years, with examples including 华夏新锦绣, 金元顺安元启, and 国金量化多策略, all maintaining positive returns for at least five consecutive years [4][5]. - 华夏新锦绣 fund, managed by 张城源, has achieved a 40.5% return this year and a cumulative return of 131.58% over five years [4]. - 金元顺安元启 fund, managed by 缪玮彬, has delivered a 29.41% return this year and a cumulative return of 262.3% over five years [5]. Group 2: Strategies Employed - Niche strategy funds utilize various strategies such as participating in private placements, quantitative stock selection, and tracking Smart Beta indices to uncover excess returns [4]. - The 定增 strategy, which involves participating in directed stock offerings at a discount, has shown promising results, with some stocks having over 50% floating profit for investors [4]. - Quantitative selection strategies have also been successful, as demonstrated by 国金量化多策略 fund, which achieved a 16.69% return this year [5]. Group 3: Market Dynamics and Company Growth - Smaller fund companies are leveraging their flexibility to quickly adapt and invest in niche strategies, leading to significant growth in fund sizes, such as 国金基金's equity fund size increasing from under 30 billion to nearly 130 billion [8]. - Larger fund companies like 华泰柏瑞 have also seen success with niche products, with their 红利低波ETF growing from 2.58 billion to 221.4 billion in size due to strong performance [9]. Group 4: Challenges Faced by Niche Strategy Funds - Niche strategy funds often face challenges such as "scale traps," where initial performance pressures can lead to significant fluctuations in fund size, risking liquidation [12]. - The effectiveness of niche strategies may require extended validation periods, and funds may be prematurely terminated during their development phase due to performance evaluations [13]. - Limited availability of niche strategy targets can lead to high concentration in holdings, increasing liquidity risks [14].