证券研究报告：金融工程报告 研究所 分析师:肖承志 SAC 登记编号:S1340524090001 Email:xiaochengzhi@cnpsec.com 近期研究报告 《大盘资金流出，中小盘资金回流— —微盘股指数周报 20250810》 - 2025.08.11 《微盘股将再次迎来高胜率区间—— 微盘股指数周报 20250803》 - 2025.08.04 《微盘股持续创新高背后的历史意义 有何不同？——微盘股指数周报 20250727》 - 2025.07.28 《微盘股的流动性风险在哪？——微 盘股指数周报 20250720》 - 2025.07.21 《上证站上 3500 点，后续关注小盘+ 科技成长——微盘股指数周报 20250713》 - 2025.07.14 《"量化新规"或将平稳落地，双均线 法再现买点——微盘股指数周报 20250706》 - 2025.07.07 《现阶段主要矛盾是交易范式之争— —微盘股指数周报 20250629》 - 2025.06.30 《调整仍不充分——微盘股指数周报 20250622》 - 2025.06.23 《短期上涨动能枯竭，控制仓位做好 防御——微盘 ...

Core Viewpoint - The micro-cap stocks have gained significant attention in the market due to their strong performance and unique characteristics, contrasting with the broader market indices which have shown limited growth [1][2]. Group 1: Market Performance - As of August 8, the micro-cap index has increased by 56.68% year-to-date, while major indices like the Shanghai Composite and CSI 300 have only shown single-digit growth [1]. - Micro-cap stocks are characterized by a "slow rise and rapid fall" pattern, indicating their potential for significant upward movement when market conditions improve [1]. Group 2: Investment Opportunities - The investment landscape for micro-cap stocks has changed, with lower crowding and improved policy environments compared to previous years [2]. - The focus on technology and innovation has been emphasized, with funds like Huian Multi-Strategy Mixed Fund targeting micro-cap stocks that have strong technological attributes and can benefit from national policies promoting innovation [2]. - Recent ratings from various securities firms have recognized the Huian Multi-Strategy Mixed Fund as a top-performing fund, indicating confidence in its strategy and potential returns [2]. Group 3: Risks and Considerations - Investment in micro-cap stocks carries inherent risks, particularly liquidity risk and delisting risk, which investors need to be aware of [3]. - The potential for liquidity issues during market downturns and the risk of companies failing to meet listing requirements are significant concerns for investors in this segment [3].

近期，多只代表中小盘乃至小微盘的指数均创下阶段性新高，涨幅相对各大宽基指数更是遥遥领先，相 关主题基金净值也取得不俗表现。 7月31日，诺安多策略宣布于8月4日起暂停5000元以上的大额限购。7月28日，中信保诚多策略公告称， 即日起暂停1000元以上大额申购、大额转换转入及大额定期定额投资业务，这是中信保诚多策略今年以 来第三次发布相关限购公告。此外，招商成长量化选股股票自7月24日起暂停20万元以上的大额申购。 部分基金选择调整策略 在基金规模猛增的情况下，除了采取限购策略以外，靠着中小盘股实现良好业绩的基金经理，有的选择 降低持股比重；还有基金经理甚至不得不将资金投向容量更大的大盘股。 以前述中信保诚多策略为例，该基金在去年规模低于7亿元时，尚能在中小盘股中"从容"地精挑细选， 然而截至今年一季度末，该基金规模增至11.99亿元，持仓个股就算占比只有2%左右，对于一些小微盘 股来说，可以轻松进入前十大股东的行列。根据今年一季报披露的持仓来看，前十大重仓股中，该基金 跻身7只股票的前十大股东。 因此，为了坚守微盘策略，且减少对公司股价的影响，二季度内基金经理继续降低了对个股的持仓权 重，所有个股的持有市值 ...

Core Viewpoint - The article emphasizes the importance of scientific thinking and critical analysis in quantitative investment, highlighting the influence of philosopher Karl Popper on investment strategies and the development of models that seek to identify and exploit market inefficiencies. Group 1: Investment Philosophy - The essence of quantitative investment lies in modeling the securities market using scientific methods to identify reproducible patterns that can influence market behavior [16][6] - The investment approach is heavily influenced by Popper's philosophy of "conjecture and refutation," which encourages the search for rules in an uncertain world [7][56] - The focus on objective analysis helps avoid the pitfalls of linear thinking and cognitive biases that can obscure judgment [2][61] Group 2: Performance Metrics - The performance of the multi-strategy fund, specifically the Nuon Multi-Strategy Mixed Fund, achieved a return of 100.74% over the past year, while the Nuon CSI 300 Index Enhanced Fund outperformed the CSI 300 Index by 2.06% with a return of 15.42% [3][29] - The significant outperformance of the Nuon Multi-Strategy Fund compared to small-cap indices like the CSI 2000 indicates that the excess returns are not merely a result of small-cap exposure but rather from sophisticated modeling techniques [3][34] Group 3: Investment Strategies - The concept of "attention value" in the A-share market suggests that investors frequently shift their focus due to the inability of many companies to meet return expectations, which can be strategically exploited for excess returns in micro-cap stocks [26][4] - The investment strategy emphasizes the importance of understanding the underlying statistical patterns and market behaviors rather than relying solely on historical performance [20][22] Group 4: Machine Learning and Model Development - The transition from multi-factor strategies to machine learning models allows for the capture of non-linear patterns, leading to superior returns that exceed human cognitive limitations [3][30] - The use of machine learning in investment models is seen as a way to enhance predictive capabilities and adapt to rapidly changing market conditions [30][40] Group 5: Market Dynamics and Future Outlook - The article argues that the excess returns from micro-cap stocks in the Chinese market are unlikely to converge due to the unique market dynamics and investor behavior [34][35] - The focus on scientific and systematic approaches in investment is expected to reveal opportunities that are not crowded, as many competitors rely on outdated inductive reasoning [45][46]

Core Viewpoint - The A-share market is experiencing a volatile adjustment phase, with significant divergence among the three major indices, indicating a need for investors to focus on individual stock fundamentals and industry trends rather than relying solely on index movements [3][5]. Market Performance - The Shanghai Composite Index closed flat with a change of 0.00%, while the Shenzhen Component Index fell by 0.08%, and the ChiNext Index declined by 0.33%, highlighting a clear divergence in market performance [3]. - The micro-cap stock index rose over 2%, reaching a new historical high, suggesting a preference among some investors for small-cap stocks due to their high elasticity and easier capital mobilization [4]. Trading Volume and Market Sentiment - Trading volume in the Shanghai and Shenzhen markets decreased significantly compared to the previous trading day, indicating a cautious sentiment among market participants [5]. - The reduction in trading volume suggests a large divergence between buyers and sellers, which may limit the market's upward potential, although it could also indicate a period of consolidation before potential recovery [5]. Sector Performance - The market displayed a clear sectoral divergence, with the port, ST, mergers and acquisitions, and food sectors showing gains, while humanoid robots, small metals, liquor, and insurance sectors experienced declines [7][8]. - The port sector's rise is attributed to marginal improvements in foreign trade data and supportive policies for the logistics industry, while the ST sector's strength is linked to expectations of asset restructuring [7]. - The decline in the humanoid robot sector is primarily due to profit-taking after previous gains, while the small metals sector is affected by fluctuations in international commodity prices [8]. Future Outlook - Despite the current market's adjustment phase, there are still structural opportunities available, particularly in sectors with strong policy support such as new energy and digital economy [10]. - Investors are advised to consider stable, reasonably valued stocks in the consumer and pharmaceutical sectors while maintaining a cautious approach to manage market volatility [10].

Quantitative Models and Construction Methods 1. Model Name: Micro-Cap Timing Model - **Model Construction Idea**: This model uses mid-term risk warning indicators to monitor market timing for micro-cap stocks, focusing on both market sentiment and fundamental indicators[29] - **Model Construction Process**: 1. Two key indicators are used: - **10-Year Treasury Yield YoY**: Measures the year-over-year change in 10-year treasury yields - **Volatility Crowding YoY**: Reflects market trading sentiment through changes in volatility 2. Risk thresholds are set for these indicators: - 10-Year Treasury Yield YoY threshold: 0.3 - Volatility Crowding YoY threshold: 0 3. If either indicator exceeds its threshold, a risk warning signal is triggered. Conversely, if both indicators fall below their thresholds, the risk warning is lifted[29][30][36] - **Model Evaluation**: The model currently does not trigger any risk warnings, suggesting a stable environment for holding micro-cap stocks[29] --- Model Backtesting Results 1. Micro-Cap Timing Model - **10-Year Treasury Yield YoY**: -28.69% (below the risk threshold of 0.3)[30] - **Volatility Crowding YoY**: -50.09% (below the risk threshold of 0)[30] --- Quantitative Factors and Construction Methods 1. Factor Name: Value Factor - **Factor Construction Idea**: Captures undervaluation by comparing financial metrics to market prices[51] - **Factor Construction Process**: 1. **Key Metrics**: - **SP_TTM**: Revenue over the past 12 months divided by the latest market capitalization - **EP_FY0**: Current annual report's expected net profit divided by the latest market capitalization - **Sales2EV**: Revenue over the past 12 months divided by enterprise value 2. These metrics are aggregated to form the value factor, with higher values indicating greater undervaluation[51] 2. Factor Name: Size Factor - **Factor Construction Idea**: Measures the impact of company size on stock performance[51] - **Factor Construction Process**: 1. **Key Metrics**: - **LN_MktCap**: Natural logarithm of free-float market capitalization - **BP_LR**: Book value per share divided by the latest market price - **EP_FTTM**: Forward 12-month expected earnings divided by the latest market price 2. These metrics are combined to represent the size factor, with smaller companies typically expected to outperform[51] 3. Factor Name: Volatility Factor - **Factor Construction Idea**: Captures the impact of price and return volatility on stock performance[51] - **Factor Construction Process**: 1. **Key Metrics**: - **IV_CAPM**: Residual volatility from the CAPM model - **IV_FF**: Residual volatility from the Fama-French three-factor model - **Price_Chg20D**: 20-day price change 2. These metrics are aggregated to form the volatility factor, with lower volatility generally preferred[51] 4. Factor Name: Reversal Factor - **Factor Construction Idea**: Exploits the tendency of stocks to revert to their mean after extreme movements[51] - **Factor Construction Process**: 1. **Key Metrics**: - **Price_Chg40D**: 40-day price change - **Price_Chg60D**: 60-day price change - **Price_Chg120D**: 120-day price change 2. These metrics are aggregated to form the reversal factor, with negative values indicating stronger reversal potential[51] 5. Factor Name: Convertible Bond Valuation Factor - **Factor Construction Idea**: Evaluates convertible bonds based on their valuation and relationship with underlying stocks[44] - **Factor Construction Process**: 1. **Key Metrics**: - **Parity Premium**: Difference between the convertible bond price and its parity value - **Underlying Stock Factors**: Includes growth, quality, and valuation metrics of the underlying stock 2. These metrics are combined to assess the attractiveness of convertible bonds[44][49] --- Factor Backtesting Results 1. Value Factor - **IC Mean**: Positive across multiple stock pools, with notable performance in the financial and real estate sectors[39][40] - **Multi-Long-Short Returns**: Positive returns observed in the past week[39][42] 2. Size Factor - **IC Mean**: Strong performance in the CSI 300 stock pool[39][41] - **Multi-Long-Short Returns**: Expected to improve as market risk appetite increases[40] 3. Volatility Factor - **IC Mean**: Stable positive returns in the A-share stock pool[39][42] - **Multi-Long-Short Returns**: Demonstrated consistent performance in recent weeks[39][42] 4. Reversal Factor - **IC Mean**: Outperformed in the CSI 500 and CSI 1000 stock pools[39][41] - **Multi-Long-Short Returns**: Positive returns observed in the past week[39][42] 5. Convertible Bond Valuation Factor - **Multi-Long-Short Returns**: Positive returns for value and valuation factors in the convertible bond market[44][48]

Investment Rating - The report maintains a positive outlook on the micro-cap stock index, indicating a favorable investment environment following regulatory changes [3][13]. Core Insights - The recent modification of the "Major Asset Restructuring Management Measures" by the China Securities Regulatory Commission allows for cross-border mergers and acquisitions, which is seen as a significant positive for micro-cap stocks [3][13]. - The micro-cap stock index has shown strong performance, ranking first among 38 broad indices over the past month with a 12.51% increase and a 68.6% increase over the past year [4][14][24]. Summary by Sections 1. Overview of Micro-Cap Stock Index Performance - The micro-cap stock index increased by 1.58% over the past week, ranking 5th among 38 indices [4][14]. - Over the past month, the index rose by 12.51%, ranking 1st [4][19]. - In the last quarter, the index saw a 17.17% increase, also ranking 1st [4][20]. - The annual performance shows a significant increase of 68.6%, ranking 2nd [4][22][24]. 2. Factor Performance of Micro-Cap Stocks - The top-performing factors this week include standardized expected earnings (0.154), leverage (0.127), and quarterly net profit growth (0.102) [5][14][28]. - The bottom-performing factors include momentum (-0.08) and growth factors (-0.032) [5][14][28]. 3. Diffusion Index Observations - The diffusion index remains high but has shown a slight decline, indicating potential sell signals if the trend continues [6][15][33]. - The first threshold method triggered a sell signal on May 8, 2025, while the delayed threshold method provided a buy signal on April 22, 2025 [6][15][36][40]. 4. Calendar Effects - The micro-cap stock index has shown positive average returns on Tuesdays and Thursdays, while Mondays and Wednesdays have negative average returns [7][16]. - The index achieved an 84% win rate in February and a 90% win rate in March and May [7][16]. 5. Micro-Cap Stock Related Fund Performance - The highest-performing micro-cap fund this week yielded 2.79%, while the lowest yielded 0.35% [16][43].

- The diffusion index model triggered a right-side buy signal at the close of trading on Tuesday, April 25, 2025 [6][14][33] - The first threshold method triggered a full position signal at the close of trading on April 7, 2025 [36] - The delayed threshold method gave an open position signal at the close of trading on April 22, 2025 [40] - The dual moving average method gave a short position signal at the close of trading on March 12, 2025 [41] Model Testing Results - Diffusion index model, weekly return 2.52% [43] - First threshold method, signal value 0.0225 [36] - Delayed threshold method, signal value not specified [40] - Dual moving average method, signal value not specified [41] Quantitative Factors and Construction - Factor name: Momentum factor; Construction idea: Based on the stock's price momentum; Construction process: Calculated using the rank IC method, weekly rank IC value 0.221, historical average -0.003 [5][13][27] - Factor name: Logarithmic market capitalization factor; Construction idea: Based on the logarithm of the stock's market capitalization; Construction process: Calculated using the rank IC method, weekly rank IC value 0.196, historical average -0.032 [5][13][27] - Factor name: Non-linear market capitalization factor; Construction idea: Based on the non-linear transformation of the stock's market capitalization; Construction process: Calculated using the rank IC method, weekly rank IC value 0.196, historical average -0.032 [5][13][27] - Factor name: Single-quarter ROE factor; Construction idea: Based on the stock's return on equity for a single quarter; Construction process: Calculated using the rank IC method, weekly rank IC value 0.19, historical average 0.025 [5][13][27] - Factor name: PE TTM reciprocal factor; Construction idea: Based on the reciprocal of the stock's price-to-earnings ratio trailing twelve months; Construction process: Calculated using the rank IC method, weekly rank IC value 0.189, historical average 0.02 [5][13][27] Factor Testing Results - Momentum factor, weekly rank IC value 0.221, historical average -0.003 [5][13][27] - Logarithmic market capitalization factor, weekly rank IC value 0.196, historical average -0.032 [5][13][27] - Non-linear market capitalization factor, weekly rank IC value 0.196, historical average -0.032 [5][13][27] - Single-quarter ROE factor, weekly rank IC value 0.19, historical average 0.025 [5][13][27] - PE TTM reciprocal factor, weekly rank IC value 0.189, historical average 0.02 [5][13][27]