证券研究报告 | 2025年10月11日 多因子选股周报 超额全线回暖，四大指增组合本周均跑赢基准 核心观点 金融工程周报 国信金工指数增强组合表现跟踪 因子表现监控 以沪深 300 指数为选股空间。最近一周，预期 EPTTM、一个月波动、BP 等因子表现较好，而单季营收同比增速、三个月机构覆盖、3 个月盈利上下 调等因子表现较差。 以中证 500 指数为选股空间。最近一周，SPTTM、预期 BP、单季 EP 等因 子表现较好，而一年动量、预期 PEG、标准化预期外收入等因子表现较差。 以中证 1000 指数为选股空间。最近一周，EPTTM、SPTTM、预期 EPTTM 等因子表现较好，而预期净利润环比、一年动量、单季营收同比增速等因子 表现较差。 以中证 A500 指数为选股空间。最近一周，单季 SP、SPTTM、一个月波动 等因子表现较好，而单季营收同比增速、一年动量、三个月机构覆盖等因子 表现较差。 以公募重仓指数为选股空间。最近一周，预期 EPTTM、单季 EP、一个月波 动等因子表现较好，而一年动量、单季营收同比增速、预期净利润环比等因 子表现较差。 公募基金指数增强产品表现跟踪 目前，公募基金沪深 ...

证券研究报告 | 2025年10月09日 金融工程月报 券商金股 2025 年 10 月投资月报 核心观点 金融工程月报 券商金股股票池上月回顾 2025 年 9 月，江波龙、协创数据、精智达等券商金股股票的月度上涨幅度 靠前。 2025 年 9 月，华安证券、华龙证券、方正证券收益排名前三，月度收益分 别为 17.45%、15.17%、14.38%，同期偏股混合型基金指数收益 5.52%， 沪深 300 指数收益 3.20%。 2025 年以来，东北证券、华鑫证券、国元证券收益排名前三，年度收益分 别为 93.33%、90.50%、69.67%，同期偏股混合型基金指数收益 35.37%， 沪深 300 指数收益 17.94%。 券商金股股票池中选股因子表现 最近一个月，日内收益率、BP、波动率表现较好，总市值、SUE、单季度 超预期幅度表现较差； 今年以来，总市值、单季度营收增速、分析师净上调幅度表现较好，波动率、 预期股息率、BP 表现较差。 券商金股股票池本月特征 截至 2025 年 10 月 9 日，共有 42 家券商发布本月金股。在对券商金股股票 池进行去重后，总共有 304 只 A 股。 从绝对占 ...

证券研究报告 | 2025年10月09日 金融工程月报 券商金股 2025 年 10 月投资月报 核心观点 金融工程月报 券商金股股票池上月回顾 2025 年 9 月，江波龙、协创数据、精智达等券商金股股票的月度上涨幅度 靠前。 2025 年以来，东北证券、华鑫证券、国元证券收益排名前三，年度收益分 别为 93.33%、90.50%、69.67%，同期偏股混合型基金指数收益 35.37%， 沪深 300 指数收益 17.94%。 券商金股股票池中选股因子表现 最近一个月，日内收益率、BP、波动率表现较好，总市值、SUE、单季度 超预期幅度表现较差； 今年以来，总市值、单季度营收增速、分析师净上调幅度表现较好，波动率、 预期股息率、BP 表现较差。 券商金股股票池本月特征 截至 2025 年 10 月 9 日，共有 42 家券商发布本月金股。在对券商金股股票 池进行去重后，总共有 304 只 A 股。 从绝对占比来看，本期券商金股在电子(16.11%)、机械(9.13%)、有色金属 (8.17%)、电力设备及新能源(6.97%)、基础化工(6.25%)行业配置较高。 从相对变化来看，本期券商金股在有色金属(+2 ...

视角下的多策略增强组合 》）为基准的增强组合，力求能稳定战胜各自基准。近期组合的表现如下 图： 国信金工指数增强组合表现如下： 二 因子表现监控 我们分别以沪深300指数、中证500指数、中证1000指数、中证A500指数及公募重仓指数为选股空间， 构造单因子MFE组合并检验其相对于各自基准的超额收益。 一、本周指数增强组合表现 沪深300指数增强组合本周超额收益-0.17%，本年超额收益16.49%。 中证500指数增强组合本周超额收益0.26%，本年超额收益8.94%。 中证1000指数增强组合本周超额收益0.91%，本年超额收益17.72%。 中证A500指数增强组合本周超额收益-0.21%，本年超额收益9.06%。 二、本周选股因子表现跟踪 沪深300成分股中单季超预期幅度、单季营收同比增速、单季ROE等因子表 现较好。 中证500成分股中三个月换手、单季营收同比增速、EPTTM一年分位点等因 子表现较好。 中证1000成分股中三个月机构覆盖、单季ROE、高管薪酬等因子表现较好。 中证A500指数成分股中单季营收同比增速、EPTTM一年分位点、单季ROE 等因子表现较好。 公募基金重仓股中高管薪酬、单 ...

证券研究报告 | 2025年09月27日 多因子选股周报 中证 1000 增强组合本周超额 0.91%，年内超额 17.72% 核心观点 金融工程周报 沪深 300 指数增强产品最近一周：超额收益最高 0.91%，最低-1.54%，中 位数-0.17%。最近一月：超额收益最高 4.81%，最低-3.36%，中位数-0.53%。 中证 500 指数增强产品最近一周：超额收益最高 1.63%，最低-1.35%，中 位数-0.01%。最近一月：超额收益最高 2.51%，最低-5.04%，中位数-0.56%。 国信金工指数增强组合表现跟踪 因子表现监控 以沪深 300 指数为选股空间。最近一周，单季超预期幅度、单季营收同比增 速、单季 ROE 等因子表现较好，而预期 BP、预期净利润环比、BP 等因子 表现较差。 以中证 500 指数为选股空间。最近一周，三个月换手、单季营收同比增速、 EPTTM 一年分位点等因子表现较好，而一年动量、标准化预期外收入、 SPTTM 等因子表现较差。 以中证 1000 指数为选股空间。最近一周，三个月机构覆盖、单季 ROE、高 管薪酬等因子表现较好，而一年动量、DELTAROA、预期 ...

国信金工指数增强组合表现跟踪 因子表现监控 以沪深 300 指数为选股空间。最近一周，单季超预期幅度、单季营收同比增 速、单季 ROE 等因子表现较好，而预期 BP、预期净利润环比、BP 等因子 表现较差。 证券研究报告 | 2025年09月27日 多因子选股周报 中证 1000 增强组合本周超额 0.91%，年内超额 17.72% 核心观点 金融工程周报 以中证 500 指数为选股空间。最近一周，三个月换手、单季营收同比增速、 EPTTM 一年分位点等因子表现较好，而一年动量、标准化预期外收入、 SPTTM 等因子表现较差。 以中证 1000 指数为选股空间。最近一周，三个月机构覆盖、单季 ROE、高 管薪酬等因子表现较好，而一年动量、DELTAROA、预期净利润环比等因 子表现较差。 以中证 A500 指数为选股空间。最近一周，单季营收同比增速、EPTTM 一 年分位点、单季 ROE 等因子表现较好，而一年动量、DELTAROA、 DELTAROE 等因子表现较差。 以公募重仓指数为选股空间。最近一周，高管薪酬、单季 ROE、三个月机 构覆盖等因子表现较好，而一年动量、预期净利润环比、预期 EPTTM 等 ...

Group 1 - The core viewpoint of the article is to track and analyze the performance of various index enhancement portfolios and the factors influencing stock selection across different indices [1][2][3][17]. Group 2 - The performance of the CSI 300 index enhancement portfolio showed an excess return of -0.65% for the week and 16.53% year-to-date [5][21]. - The CSI 500 index enhancement portfolio had an excess return of -0.37% for the week and 8.50% year-to-date [5][23]. - The CSI 1000 index enhancement portfolio recorded an excess return of -0.53% for the week and 16.52% year-to-date [5][26]. - The CSI A500 index enhancement portfolio achieved an excess return of 0.02% for the week and 9.22% year-to-date [5][27]. Group 3 - In the CSI 300 component stocks, factors such as one-year momentum, quarterly revenue growth year-on-year, and three-month institutional coverage performed well [6][8]. - In the CSI 500 component stocks, factors like executive compensation, standardized expected non-operating income, and quarterly revenue growth year-on-year showed strong performance [6][10]. - For the CSI 1000 component stocks, factors such as expected PEG, standardized expected non-operating income, and three-month institutional coverage performed well [6][12]. - In the CSI A500 index component stocks, factors like executive compensation, three-month institutional coverage, and quarterly revenue growth year-on-year were notable [6][14]. Group 4 - The public fund index enhancement products for the CSI 300 had a maximum excess return of 1.16% and a minimum of -1.26% for the week, with a median of -0.17% [21][19]. - The CSI 500 public fund index enhancement products had a maximum excess return of 1.09% and a minimum of -1.70% for the week, with a median of -0.25% [23][20]. - The CSI 1000 public fund index enhancement products recorded a maximum excess return of 0.96% and a minimum of -1.05% for the week, with a median of -0.08% [26][24]. - The CSI A500 public fund index enhancement products achieved a maximum excess return of 0.77% and a minimum of -0.96% for the week, with a median of -0.07% [27][25].

Quantitative Models and Construction Methods 1. Model Name: Maximized Factor Exposure Portfolio (MFE) - **Model Construction Idea**: The MFE portfolio is designed to test the effectiveness of individual factors under realistic constraints, such as industry exposure, style exposure, stock weight deviation, and turnover rate. This approach ensures that the factors deemed "effective" can genuinely contribute to the portfolio's predictive power in real-world scenarios [39][40]. - **Model Construction Process**: - The optimization model maximizes single-factor exposure while adhering to constraints such as style and industry neutrality, stock weight limits, and turnover control. - The objective function is expressed as: $ \begin{array}{ll} max & f^{T} w \\ s.t. & s_{l} \leq X(w-w_{b}) \leq s_{h} \\ & h_{l} \leq H(w-w_{b}) \leq h_{h} \\ & w_{l} \leq w-w_{b} \leq w_{h} \\ & b_{l} \leq B_{b}w \leq b_{h} \\ & \mathbf{0} \leq w \leq l \\ & \mathbf{1}^{T} w = 1 \end{array} $ - **Explanation**: - \( f \): Factor values - \( w \): Stock weight vector - \( X \): Style factor exposure matrix - \( H \): Industry exposure matrix - \( w_b \): Benchmark stock weights - \( s_l, s_h \): Lower and upper bounds for style exposure - \( h_l, h_h \): Lower and upper bounds for industry exposure - \( w_l, w_h \): Lower and upper bounds for stock weight deviation - \( b_l, b_h \): Lower and upper bounds for benchmark stock weight proportions [39][40] - The process involves: 1. Setting constraints for style, industry, and stock weight deviations 2. Constructing the MFE portfolio at the end of each month 3. Backtesting the portfolio with historical data, accounting for transaction costs [41][43] - **Model Evaluation**: The MFE model is effective in testing factor performance under realistic constraints, ensuring that selected factors contribute to portfolio returns in practical scenarios [39][40] --- Factor Construction and Methods 1. Factor Name: Standardized Unexpected Earnings (SUE) - **Factor Construction Idea**: SUE measures the deviation of actual earnings from expected earnings, standardized by the standard deviation of expected earnings. It captures the market's reaction to earnings surprises [17]. - **Factor Construction Process**: - Formula: $ SUE = \frac{(Actual\ Net\ Profit - Expected\ Net\ Profit)}{Standard\ Deviation\ of\ Expected\ Net\ Profit} $ - Parameters: - Actual Net Profit: Reported earnings for the quarter - Expected Net Profit: Consensus analyst estimates for the quarter - Standard Deviation of Expected Net Profit: Variability in analyst estimates [17] 2. Factor Name: Momentum (1-Year Momentum) - **Factor Construction Idea**: Momentum captures the tendency of stocks with strong past performance to continue outperforming in the near term [17]. - **Factor Construction Process**: - Formula: $ Momentum = \text{Cumulative Return over the Past Year (Excluding the Most Recent Month)} $ - Parameters: - Cumulative Return: Total return over the specified period, excluding the most recent month to avoid short-term reversal effects [17] 3. Factor Name: Single-Quarter Revenue Growth (YoY) - **Factor Construction Idea**: This factor measures the year-over-year growth in quarterly revenue, reflecting a company's growth potential [17]. - **Factor Construction Process**: - Formula: $ Revenue\ Growth = \frac{(Current\ Quarter\ Revenue - Revenue\ from\ Same\ Quarter\ Last\ Year)}{Revenue\ from\ Same\ Quarter\ Last\ Year} $ - Parameters: - Current Quarter Revenue: Revenue reported for the current quarter - Revenue from Same Quarter Last Year: Revenue reported for the same quarter in the previous year [17] --- Factor Backtesting Results 1. Factor: 1-Year Momentum - **Performance**: - **CSI 300 Universe**: Weekly excess return of 0.67%, monthly excess return of 3.06%, annualized historical return of 2.70% [19] - **CSI 500 Universe**: Weekly excess return of 0.92%, monthly excess return of 0.21%, annualized historical return of 3.07% [21] - **CSI 1000 Universe**: Weekly excess return of -0.27%, monthly excess return of -2.23%, annualized historical return of -0.46% [23] 2. Factor: Single-Quarter Revenue Growth (YoY) - **Performance**: - **CSI 300 Universe**: Weekly excess return of 0.66%, monthly excess return of 4.36%, annualized historical return of 4.93% [19] - **CSI 500 Universe**: Weekly excess return of 1.05%, monthly excess return of 2.95%, annualized historical return of 3.70% [21] - **CSI 1000 Universe**: Weekly excess return of -0.16%, monthly excess return of 4.94%, annualized historical return of 5.11% [23] 3. Factor: Standardized Unexpected Earnings (SUE) - **Performance**: - **CSI 300 Universe**: Weekly excess return of 0.02%, monthly excess return of 1.49%, annualized historical return of 3.98% [19] - **CSI 500 Universe**: Weekly excess return of 0.35%, monthly excess return of 0.22%, annualized historical return of 9.14% [21] - **CSI 1000 Universe**: Weekly excess return of -1.37%, monthly excess return of 0.77%, annualized historical return of 10.44% [23] --- Model Backtesting Results 1. CSI 300 Enhanced Portfolio - Weekly excess return: -0.65% - Year-to-date excess return: 16.53% [5][14] 2. CSI 500 Enhanced Portfolio - Weekly excess return: -0.37% - Year-to-date excess return: 8.50% [5][14] 3. CSI 1000 Enhanced Portfolio - Weekly excess return: -0.53% - Year-to-date excess return: 16.52% [5][14] 4. CSI A500 Enhanced Portfolio - Weekly excess return: 0.02% - Year-to-date excess return: 9.22% [5][14]

Group 1: Weekly Index Enhanced Portfolio Performance - The CSI 300 index enhanced portfolio achieved an excess return of 0.61% this week and 17.47% year-to-date [1][6] - The CSI 500 index enhanced portfolio recorded an excess return of -0.85% this week and 8.97% year-to-date [1][6] - The CSI 1000 index enhanced portfolio had an excess return of -0.05% this week and 17.24% year-to-date [1][6] - The CSI A500 index enhanced portfolio reported an excess return of -0.55% this week and 9.19% year-to-date [1][6] Group 2: Stock Selection Factor Performance Tracking - In the CSI 300 component stocks, factors such as three-month institutional coverage, one-month volatility, and one-year momentum performed well [1][7] - In the CSI 500 component stocks, one-year momentum, expected net profit month-on-month, and single-quarter revenue year-on-year growth showed strong performance [1][7] - In the CSI 1000 component stocks, single-quarter EP, three-month earnings adjustments, and single-quarter ROE were notable factors [1][7] - In the CSI A500 index component stocks, one-year momentum, standardized expected external income, and single-quarter revenue year-on-year growth performed well [1][7] - Among public fund heavy stocks, one-year momentum, single-quarter revenue year-on-year growth, and expected net profit month-on-month were strong factors [1][7] Group 3: Public Fund Index Enhanced Product Performance Tracking - The CSI 300 index enhanced products had a maximum excess return of 2.13%, a minimum of -1.11%, and a median of 0.05% this week [1][20] - The CSI 500 index enhanced products had a maximum excess return of 0.44%, a minimum of -1.86%, and a median of -0.42% this week [1][22] - The CSI 1000 index enhanced products had a maximum excess return of 0.63%, a minimum of -1.37%, and a median of 0.03% this week [1][26] - The CSI A500 index enhanced products had a maximum excess return of 0.84%, a minimum of -0.79%, and a median of -0.02% this week [1][27]

Group 1 - The core viewpoint of the article is to track the performance of various index enhancement portfolios and the factors influencing stock selection across different indices [1][2][22] - The HuShen 300 index enhancement portfolio achieved an excess return of 0.86% this week and 16.44% year-to-date [8][22] - The CSI 500 index enhancement portfolio recorded an excess return of -0.49% this week and 9.76% year-to-date [8][22] - The CSI 1000 index enhancement portfolio had an excess return of 1.46% this week and 16.90% year-to-date [8][22] - The CSI A500 index enhancement portfolio saw an excess return of 0.69% this week and 9.70% year-to-date [8][22] Group 2 - In the HuShen 300 component stocks, factors such as single-season ROE, expected EPTTM, and single-season EP performed well [9][11] - In the CSI 500 component stocks, factors like expected PEG, single-season SP, and SPTTM showed strong performance [10][12] - For the CSI 1000 component stocks, factors including single-season revenue year-on-year growth, three-month reversal, and expected PEG performed well [14][15] - In the CSI A500 index component stocks, single-season ROE, single-season EP, and EPTTM were among the top-performing factors [17][18] Group 3 - The public fund index enhancement products showed varying excess returns, with the HuShen 300 index enhancement product having a maximum excess return of 1.44% and a minimum of -0.86% this week [25][26] - The CSI 500 index enhancement product had a maximum excess return of 1.48% and a minimum of -1.21% this week [26][28] - The CSI 1000 index enhancement product recorded a maximum excess return of 1.32% and a minimum of -0.81% this week [28][29] - The CSI A500 index enhancement product achieved a maximum excess return of 1.52% and a minimum of -0.87% this week [28][29]