证券研究报告 | 2026年03月02日 金融工程月报 券商金股 2026 年 3 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 2026 年 2 月，炬光科技、东方钽业、天孚通信等券商金股股票的月度上涨 幅度靠前。 2026 年 2 月，财通证券、东吴证券、国投证券收益排名前三，月度收益分 别为 14.54%、10.54%、9.85%，同期偏股混合型基金指数收益 1.04%，沪 深 300 指数收益 0.09%。 2026 年以来，国元证券、中邮证券、东吴证券收益排名前三，年度收益分 别为 25.15%、24.81%、21.17%，同期偏股混合型基金指数收益 8.44%， 沪深 300 指数收益 1.74%。 券商金股股票池中选股因子表现 最近一个月，总市值、SUE、预期股息率表现较好，EPTTM、剥离涨停动 量、日内收益率表现较差； 今年以来，总市值、分析师净上调比例、分析师净上调幅度表现较好，单季 度 ROE、EPTTM、日内收益率表现较差。 券商金股股票池本月特征 截至 2026 年 3 月 2 日，共有 39 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 273 只 A ...

以沪深 300 指数为选股空间。最近一周，标准化预期外收入、预期 PEG、 DELTAROE 等因子表现较好，而非流动性冲击、一个月反转、三个月波动 等因子表现较差。 证券研究报告 | 2026年02月28日 多因子选股周报 估值因子表现出色，中证 A500 增强组合年内超额 3.78% 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 以中证 500 指数为选股空间。最近一周，预期 BP、BP、SPTTM 等因子表 现较好，而预期净利润环比、三个月反转、三个月换手等因子表现较差。 以中证 1000 指数为选股空间。最近一周，SPTTM、一年动量、单季 SP 等 因子表现较好，而 DELTAROA、一个月换手、一个月反转等因子表现较差。 以中证 A500 指数为选股空间。最近一周，特异度、标准化预期外收入、预 期 PEG 等因子表现较好，而 EPTTM 一年分位点、三个月换手、预期净利 润环比等因子表现较差。 以公募重仓指数为选股空间。最近一周，一年动量、单季 SP、单季营利同 比增速等因子表现较好，而非流动性冲击、三个月反转、一个月波动等因子 表现较差。 公募基金指数增强产品表现跟踪 目前 ...

Quantitative Models and Construction Methods - **Model Name**: Maximized Factor Exposure Portfolio (MFE) **Model Construction Idea**: The MFE portfolio is designed to test the effectiveness of single factors under real-world constraints, such as industry exposure, style exposure, stock weight limits, and turnover rate. This approach ensures that factors deemed "effective" can genuinely contribute to return prediction in the final portfolio[39][40]. **Model Construction Process**: The MFE portfolio is constructed using the following optimization model: $ \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} $ - **Objective Function**: Maximize single-factor exposure, where \( f \) represents factor values, \( f^{T}w \) is the weighted exposure of the portfolio to the factor, and \( w \) is the stock weight vector. - **Constraints**: 1. **Style Exposure**: \( X \) is the factor exposure matrix for stocks, \( w_b \) is the benchmark weight vector, and \( s_l, s_h \) are the lower and upper bounds for style factor exposure. 2. **Industry Exposure**: \( H \) is the industry exposure matrix, where \( H_{ij} = 1 \) if stock \( i \) belongs to industry \( j \), and \( h_l, h_h \) are the lower and upper bounds for industry deviation. 3. **Stock Deviation**: \( w_l, w_h \) are the lower and upper bounds for individual stock deviations from the benchmark. 4. **Constituent Weight**: \( B_b \) is a 0-1 vector indicating whether a stock is a benchmark constituent, and \( b_l, b_h \) are the lower and upper bounds for constituent weights. 5. **No Short Selling**: Ensures non-negative weights and limits individual stock weights to \( l \). 6. **Full Investment**: Ensures the portfolio is fully invested with \( \mathbf{1}^{T}w = 1 \)[39][40][41]. **Model Evaluation**: The MFE portfolio effectively tests factor performance under realistic constraints, making it a robust tool for evaluating factor predictability in practical scenarios[39][40]. --- Quantitative Factors and Construction Methods - **Factor Name**: Standardized Unexpected Earnings (SUE) **Factor Construction Idea**: Measures the deviation of actual quarterly net profit from expected profit, standardized by the standard deviation of expected profit. This factor captures earnings surprises[17]. **Factor Construction Process**: $ SUE = \frac{\text{Actual Quarterly Net Profit} - \text{Expected Quarterly Net Profit}}{\text{Standard Deviation of Expected Net Profit}} $ **Factor Evaluation**: SUE is a growth-related factor and has shown strong performance in certain market conditions, particularly in capturing earnings surprises[17]. - **Factor Name**: One-Year Momentum **Factor Construction Idea**: Measures the momentum of stock prices over the past year, excluding the most recent month, to avoid short-term reversals[17]. **Factor Construction Process**: $ \text{One-Year Momentum} = \text{Cumulative Return Over the Past Year (Excluding the Last Month)} $ **Factor Evaluation**: This factor is widely used in momentum strategies and has demonstrated consistent performance in various market environments[17]. - **Factor Name**: Three-Month Earnings Revision **Factor Construction Idea**: Tracks the net number of analyst upgrades versus downgrades over the past three months, normalized by the total number of analysts covering the stock[17]. **Factor Construction Process**: $ \text{Three-Month Earnings Revision} = \frac{\text{Number of Upgrades} - \text{Number of Downgrades}}{\text{Total Number of Analysts}} $ **Factor Evaluation**: This factor reflects changes in market sentiment and has shown strong predictive power for short-term stock performance[17]. --- Backtesting Results of Models - **MFE Portfolio Performance**: - **CSI 300 Index**: Weekly excess return: -0.14%; YTD excess return: 3.07%[5][14]. - **CSI 500 Index**: Weekly excess return: -0.27%; YTD excess return: -0.57%[5][14]. - **CSI 1000 Index**: Weekly excess return: -0.69%; YTD excess return: 3.24%[5][14]. - **CSI A500 Index**: Weekly excess return: 0.12%; YTD excess return: 3.43%[5][14]. --- Backtesting Results of Factors - **Standardized Unexpected Earnings (SUE)**: - **CSI 300 Index**: Weekly excess return: 0.31%; Monthly excess return: -0.50%; YTD excess return: 0.16%[19]. - **CSI 500 Index**: Weekly excess return: 0.77%; Monthly excess return: -0.02%; YTD excess return: 0.11%[21]. - **CSI 1000 Index**: Weekly excess return: 0.31%; Monthly excess return: 0.40%; YTD excess return: -1.04%[23]. - **CSI A500 Index**: Weekly excess return: 0.65%; Monthly excess return: -0.68%; YTD excess return: 0.46%[25]. - **One-Year Momentum**: - **CSI 300 Index**: Weekly excess return: 0.54%; Monthly excess return: 0.74%; YTD excess return: 0.36%[19]. - **CSI 500 Index**: Weekly excess return: 0.08%; Monthly excess return: -0.56%; YTD excess return: -1.95%[21]. - **CSI 1000 Index**: Weekly excess return: -0.33%; Monthly excess return: -0.12%; YTD excess return: 1.52%[23]. - **CSI A500 Index**: Weekly excess return: 0.66%; Monthly excess return: -0.96%; YTD excess return: -1.32%[25]. - **Three-Month Earnings Revision**: - **CSI 300 Index**: Weekly excess return: 0.19%; Monthly excess return: -0.47%; YTD excess return: -0.04%[19]. - **CSI 500 Index**: Weekly excess return: 1.02%; Monthly excess return: 2.06%; YTD excess return: 0.80%[21]. - **CSI 1000 Index**: Weekly excess return: 0.31%; Monthly excess return: 2.78%; YTD excess return: 3.88%[23]. - **CSI A500 Index**: Weekly excess return: 0.02%; Monthly excess return: 0.53%; YTD excess return: 0.56%[25].

Group 1 - The performance of the CSI 300 index enhanced portfolio showed an excess return of 0.24% this week and 3.21% year-to-date [6][18] - The CSI 500 index enhanced portfolio had an excess return of 0.53% this week but a negative return of -0.27% year-to-date [6][18] - The CSI 1000 index enhanced portfolio achieved an excess return of 1.63% this week and 3.92% year-to-date [6][18] - The CSI A500 index enhanced portfolio recorded an excess return of 0.40% this week and 3.28% year-to-date [6][18] Group 2 - In the CSI 300 component stocks, factors such as single-season SP, SPTTM, and single-season EP performed well [7][9] - For CSI 500 component stocks, factors like one-month volatility, three-month reversal, and one-month reversal showed strong performance [9][11] - In the CSI 1000 component stocks, one-month reversal, three-month reversal, and non-liquidity shock factors performed well [9][13] - The CSI A500 index component stocks saw good performance from one-month volatility, single-season EP, and three-month turnover factors [9][15] Group 3 - The CSI 300 index enhanced products had a maximum excess return of 1.24% and a minimum of -1.45% this week, with a median of 0.11% [22] - The CSI 500 index enhanced products had a maximum excess return of 1.27% and a minimum of -0.80% this week, with a median of 0.24% [23] - The CSI 1000 index enhanced products had a maximum excess return of 1.54% and a minimum of -0.91% this week, with a median of 0.22% [25] - The CSI A500 index enhanced products had a maximum excess return of 1.28% and a minimum of -1.99% this week, with a median of 0.14% [29]

- The report tracks the performance of Guosen Financial Engineering's index enhancement portfolios, which are constructed based on benchmarks such as CSI 300, CSI 500, CSI 1000, and CSI A500 indices, aiming to consistently outperform their respective benchmarks [11][12][14] - The construction process of the index enhancement portfolios includes three main components: return prediction, risk control, and portfolio optimization [12] - The report monitors the performance of common stock selection factors across different stock selection spaces, including CSI 300, CSI 500, CSI 1000, CSI A500, and public fund heavy-holding indices, by constructing single-factor Maximized Factor Exposure (MFE) portfolios and tracking their relative excess returns [11][15][42] - The MFE portfolio construction process involves optimizing the portfolio to maximize single-factor exposure while controlling for various constraints such as industry exposure, style exposure, stock weight deviation, turnover rate, and component stock weight proportion [42][43][44] - The optimization model for MFE portfolios is expressed as follows: $\begin{array}{ll}max&f^{T}\ w\\ s.t.&s_{l}\leq X(w-w_{b})\leq s_{h}\\ &h_{l}\leq H(w-w_{b})\leq h_{h}\\ &w_{l}\leq w-w_{b}\leq w_{h}\\ &b_{l}\leq B_{b}w\leq b_{h}\\ &\mathbf{0}\leq w\leq l\\ &\mathbf{1}^{T}\ w=1\end{array}$ where `f` represents factor values, `w` is the stock weight vector, and constraints include style factor deviation, industry deviation, stock weight deviation, component stock weight proportion, and stock weight limits [42][43] - The report provides detailed performance tracking of single-factor MFE portfolios across different stock selection spaces, highlighting factors such as SP, SPTTM, EP, and others that performed well in specific indices like CSI 300, CSI 500, CSI 1000, CSI A500, and public fund heavy-holding indices [15][18][20][22][24][26] - The report also tracks the excess returns of public fund index enhancement products, including CSI 300, CSI 500, CSI 1000, and CSI A500, with detailed statistics on maximum, minimum, and median excess returns over different time periods [28][32][35][38][41]

Quantitative Models and Factor Analysis Quantitative Models and Construction Methods Model Name: Guosen JinGong Index Enhanced Portfolio - **Model Construction Idea**: The model aims to outperform its respective benchmarks by constructing enhanced portfolios based on multiple factors[11][12]. - **Model Construction Process**: 1. **Return Prediction**: Predicting the returns of stocks within the benchmark index. 2. **Risk Control**: Implementing risk control measures to manage the portfolio's risk exposure. 3. **Portfolio Optimization**: Optimizing the portfolio to maximize returns while adhering to the risk constraints[12]. - **Model Evaluation**: The model is designed to consistently outperform its benchmarks by leveraging multiple factors[11]. Model Backtesting Results - **Guosen JinGong Index Enhanced Portfolio**: - **CSI 300 Index Enhanced Portfolio**: Weekly excess return 0.24%, annual excess return 3.21%[5][14]. - **CSI 500 Index Enhanced Portfolio**: Weekly excess return 0.53%, annual excess return -0.27%[5][14]. - **CSI 1000 Index Enhanced Portfolio**: Weekly excess return 1.63%, annual excess return 3.92%[5][14]. - **CSI A500 Index Enhanced Portfolio**: Weekly excess return 0.40%, annual excess return 3.28%[5][14]. Quantitative Factors and Construction Methods Factor Name: Single-Season SP - **Factor Construction Idea**: This factor measures the ratio of single-quarter operating revenue to total market value[17]. - **Factor Construction Process**: - Formula: $ \text{Single-Season SP} = \frac{\text{Single-Quarter Operating Revenue}}{\text{Total Market Value}} $[17]. - **Factor Evaluation**: This factor performed well in the CSI 300 and public fund heavy index selection spaces[1][26]. Factor Name: Single-Season EP - **Factor Construction Idea**: This factor measures the ratio of single-quarter net profit attributable to the parent company to total market value[17]. - **Factor Construction Process**: - Formula: $ \text{Single-Season EP} = \frac{\text{Single-Quarter Net Profit Attributable to Parent}}{\text{Total Market Value}} $[17]. - **Factor Evaluation**: This factor performed well in the CSI 300 and CSI A500 index selection spaces[1][24]. Factor Name: SPTTM - **Factor Construction Idea**: This factor measures the ratio of trailing twelve months (TTM) operating revenue to total market value[17]. - **Factor Construction Process**: - Formula: $ \text{SPTTM} = \frac{\text{TTM Operating Revenue}}{\text{Total Market Value}} $[17]. - **Factor Evaluation**: This factor performed well in the CSI 300 and public fund heavy index selection spaces[1][26]. Factor Name: One-Month Reversal - **Factor Construction Idea**: This factor measures the price change over the past 20 trading days[17]. - **Factor Construction Process**: - Formula: $ \text{One-Month Reversal} = \text{Price Change over Past 20 Trading Days} $[17]. - **Factor Evaluation**: This factor performed well in the CSI 500 and CSI 1000 index selection spaces[1][20][22]. Factor Name: Three-Month Reversal - **Factor Construction Idea**: This factor measures the price change over the past 60 trading days[17]. - **Factor Construction Process**: - Formula: $ \text{Three-Month Reversal} = \text{Price Change over Past 60 Trading Days} $[17]. - **Factor Evaluation**: This factor performed well in the CSI 500 and CSI 1000 index selection spaces[1][20][22]. Factor Name: Non-Liquidity Shock - **Factor Construction Idea**: This factor measures the average absolute value of daily price changes over the past 20 trading days divided by the average trading volume[17]. - **Factor Construction Process**: - Formula: $ \text{Non-Liquidity Shock} = \frac{\text{Average Absolute Daily Price Change}}{\text{Average Trading Volume}} $[17]. - **Factor Evaluation**: This factor performed well in the CSI 1000 index selection space[1][22]. Factor Backtesting Results - **Single-Season SP**: - **CSI 300**: Weekly excess return 1.33%, monthly excess return 0.89%, annualized historical return 2.80%[19]. - **Public Fund Heavy Index**: Weekly excess return 1.45%, monthly excess return 1.56%, annualized historical return 1.98%[26]. - **Single-Season EP**: - **CSI 300**: Weekly excess return 0.99%, monthly excess return 1.48%, annualized historical return 5.37%[19]. - **CSI A500**: Weekly excess return 1.29%, monthly excess return 1.59%, annualized historical return 5.16%[24]. - **SPTTM**: - **CSI 300**: Weekly excess return 1.11%, monthly excess return 0.81%, annualized historical return 2.03%[19]. - **Public Fund Heavy Index**: Weekly excess return 1.44%, monthly excess return 1.09%, annualized historical return 0.76%[26]. - **One-Month Reversal**: - **CSI 500**: Weekly excess return 1.19%, monthly excess return -0.32%, annualized historical return -1.60%[20]. - **CSI 1000**: Weekly excess return 1.77%, monthly excess return -0.37%, annualized historical return -4.29%[22]. - **Three-Month Reversal**: - **CSI 500**: Weekly excess return 1.42%, monthly excess return -3.14%, annualized historical return -2.38%[20]. - **CSI 1000**: Weekly excess return 1.56%, monthly excess return 0.76%, annualized historical return -1.95%[22]. - **Non-Liquidity Shock**: - **CSI 1000**: Weekly excess return 1.52%, monthly excess return 2.73%, annualized historical return 2.48%[22].

- The quantitative factors that performed well in the broker gold stock pool over the past month include total market capitalization, single-quarter net profit growth rate, and analyst net upgrade ratio[3][30] - The quantitative factors that performed poorly in the broker gold stock pool over the past month include post-earnings announcement gap excess, single-quarter ROE, and intraday return rate[3][30] - The broker gold stock performance enhancement portfolio achieved an absolute return of 11.47% and an excess return of 4.15% relative to the partial equity hybrid fund index for the period from January 5, 2026, to January 30, 2026[5][43] - The broker gold stock performance enhancement portfolio ranked in the 16.69th percentile among active equity funds for the period from January 5, 2026, to January 30, 2026[5][43] - The broker gold stock index achieved a return of 7.60% for the period from January 5, 2026, to January 30, 2026, compared to a return of 7.32% for the partial equity hybrid fund index over the same period[24]

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][5][18]. Group 2 - The performance of the CSI 300 index enhancement portfolio this week showed an excess return of 0.00%, with a year-to-date excess return of 3.00% [6][22]. - The CSI 500 index enhancement portfolio had an excess return of 0.01% this week, but a year-to-date excess return of -0.88% [6][24]. - The CSI 1000 index enhancement portfolio achieved an excess return of 0.90% this week, with a year-to-date excess return of 2.17% [6][25]. - The CSI A500 index enhancement portfolio reported an excess return of -0.53% this week, with a year-to-date excess return of 2.90% [6][28]. Group 3 - In the CSI 300 component stocks, factors such as expected PEG, quarterly ROA, and EPTTM performed well [7][9]. - In the CSI 500 component stocks, factors like dividend yield, EPTTM, and BP showed strong performance [11][10]. - For the CSI 1000 component stocks, factors including quarterly ROA, quarterly ROE, and standardized expected non-operating income performed well [13][12]. - In the CSI A500 index component stocks, factors such as dividend yield, quarterly revenue growth year-on-year, and quarterly ROA were notable [15][14]. Group 4 - The public fund index enhancement products for the CSI 300 had a maximum excess return of 1.08% and a minimum of -1.05% this week, with a median of -0.02% [22][20]. - The CSI 500 index enhancement products had a maximum excess return of 1.72% and a minimum of -0.67% this week, with a median of 0.29% [24][23]. - The CSI 1000 index enhancement products reported a maximum excess return of 0.96% and a minimum of -0.97% this week, with a median of 0.18% [26][25]. - The CSI A500 index enhancement products had a maximum excess return of 1.14% and a minimum of -1.73% this week, with a median of -0.00% [28][27].

Quantitative Models and Factor Analysis Summary Quantitative Models and Construction Methods Model Name: Guosen JinGong Index Enhanced Portfolio - **Model Construction Idea**: The model aims to outperform its respective benchmarks by constructing enhanced portfolios based on multiple factors[11] - **Model Construction Process**: - **Return Prediction**: Predicting the returns of stocks within the benchmark index - **Risk Control**: Implementing risk control measures to manage portfolio risk - **Portfolio Optimization**: Optimizing the portfolio to maximize returns while adhering to constraints such as industry exposure, style exposure, stock weight deviation, and turnover rate[12] - **Model Evaluation**: The model is designed to consistently outperform its benchmarks by leveraging multiple factors[11] Model Backtesting Results Guosen JinGong Index Enhanced Portfolio - **CSI 300 Index Enhanced Portfolio**: - Weekly Excess Return: 0.00% - Year-to-Date Excess Return: 3.00%[5][14] - **CSI 500 Index Enhanced Portfolio**: - Weekly Excess Return: 0.01% - Year-to-Date Excess Return: -0.88%[5][14] - **CSI 1000 Index Enhanced Portfolio**: - Weekly Excess Return: 0.90% - Year-to-Date Excess Return: 2.17%[5][14] - **CSI A500 Index Enhanced Portfolio**: - Weekly Excess Return: -0.53% - Year-to-Date Excess Return: 2.90%[5][14] Quantitative Factors and Construction Methods Factor Name: Dividend Yield - **Factor Construction Idea**: Measures the dividend income relative to the stock price, indicating the return on investment from dividends[17] - **Factor Construction Process**: - Formula: $\text{Dividend Yield} = \frac{\text{Dividend per Share}}{\text{Stock Price}}$ - The factor is calculated as the sum of the dividends declared over the last four quarters divided by the current market capitalization[17] - **Factor Evaluation**: The dividend yield factor is effective in identifying stocks with high dividend returns, which can be attractive to income-focused investors[17] Factor Name: EPTTM (Earnings to Price TTM) - **Factor Construction Idea**: Measures the earnings relative to the stock price over the trailing twelve months, indicating the profitability of the company[17] - **Factor Construction Process**: - Formula: $\text{EPTTM} = \frac{\text{Earnings TTM}}{\text{Market Capitalization}}$ - The factor is calculated as the total earnings over the trailing twelve months divided by the current market capitalization[17] - **Factor Evaluation**: The EPTTM factor is useful for identifying undervalued stocks with strong earnings performance[17] Factor Name: BP (Book to Price) - **Factor Construction Idea**: Measures the book value relative to the stock price, indicating the intrinsic value of the company[17] - **Factor Construction Process**: - Formula: $\text{BP} = \frac{\text{Book Value}}{\text{Market Capitalization}}$ - The factor is calculated as the book value of equity divided by the current market capitalization[17] - **Factor Evaluation**: The BP factor helps in identifying stocks that are potentially undervalued based on their book value[17] Factor Backtesting Results CSI 300 Index Sample Space - **Best Performing Factors (Recent Week)**: Expected PEG, Single Quarter ROA, EPTTM[1][19] - **Worst Performing Factors (Recent Week)**: Three-Month Reversal, Expected Net Profit QoQ, One-Month Turnover[1][19] CSI 500 Index Sample Space - **Best Performing Factors (Recent Week)**: Dividend Yield, EPTTM, BP[1][20] - **Worst Performing Factors (Recent Week)**: Expected Net Profit QoQ, Single Quarter Operating Profit YoY Growth, Three-Month Institutional Coverage[1][20] CSI 1000 Index Sample Space - **Best Performing Factors (Recent Week)**: Single Quarter ROA, Single Quarter ROE, Standardized Unexpected Revenue[1][22] - **Worst Performing Factors (Recent Week)**: One-Month Reversal, Single Quarter Net Profit YoY Growth, Three-Month Reversal[1][22] CSI A500 Index Sample Space - **Best Performing Factors (Recent Week)**: Dividend Yield, Single Quarter Revenue YoY Growth, Single Quarter ROA[1][24] - **Worst Performing Factors (Recent Week)**: Expected Net Profit QoQ, Single Quarter Net Profit YoY Growth, Single Quarter Operating Profit YoY Growth[1][24] Public Fund Heavy Index Sample Space - **Best Performing Factors (Recent Week)**: Dividend Yield, Single Quarter ROA, DELTAROA[1][27] - **Worst Performing Factors (Recent Week)**: Three-Month Reversal, Three-Month Institutional Coverage, Single Quarter Net Profit YoY Growth[1][27]

- The report tracks the performance of Guosen Financial Engineering's index enhancement portfolios, which are constructed using multi-factor stock selection models targeting benchmarks such as CSI 300, CSI 500, CSI 1000, and CSI A500 indices[11][12][14] - The construction process of the index enhancement portfolios includes three main components: return prediction, risk control, and portfolio optimization[12] - Single-factor Maximized Factor Exposure (MFE) portfolios are constructed for each factor within different stock selection spaces (e.g., CSI 300, CSI 500, CSI 1000, CSI A500, and public fund heavy positions index) to evaluate the effectiveness of individual factors under real-world constraints[15][40][41] - The optimization model for MFE portfolios aims to maximize single-factor exposure while controlling for constraints such as style exposure, industry exposure, individual stock weight deviation, component stock weight proportion, and individual stock weight limits[40][41][42] - The formula for the optimization model is: $\begin{array}{ll}max&f^{T}\ w\\ s.t.&s_{l}\leq X(w-w_{b})\leq s_{h}\\ &h_{l}\leq H(w-w_{b})\leq h_{h}\\ &w_{l}\leq w-w_{b}\leq w_{h}\\ &b_{l}\leq B_{b}w\leq b_{h}\\ &\mathbf{0}\leq w\leq l\\ &\mathbf{1}^{T}\ w=1\end{array}$ where `f` represents factor values, `w` is the stock weight vector, and constraints include style, industry, and stock-specific limits[40][41] - Factors are categorized into valuation, reversal, growth, profitability, liquidity, volatility, corporate governance, and analyst dimensions, with over 30 factors tracked, such as BP, EPTTM, ROA, ROE, and dividend yield[16][17] - Factor performance varies across different stock selection spaces. For example, in the CSI 300 space, factors like expected PEG, single-quarter ROA, and EPTTM performed well recently, while factors like three-month reversal and one-month turnover performed poorly[19] - In the CSI 500 space, factors such as dividend yield, EPTTM, and BP showed strong performance recently, while factors like three-month reversal and single-quarter profit growth rate underperformed[20][21] - In the CSI 1000 space, factors like single-quarter ROA, single-quarter ROE, and standardized unexpected income performed well, while factors like one-month reversal and three-month reversal lagged[22][23] - In the CSI A500 space, factors such as dividend yield, single-quarter revenue growth rate, and single-quarter ROA performed well, while factors like expected net profit quarter-on-quarter and single-quarter profit growth rate underperformed[24][25] - In the public fund heavy positions index space, factors like dividend yield, single-quarter ROA, and DELTAROA performed well recently, while factors like three-month reversal and single-quarter profit growth rate lagged[26][27] - The report also tracks the performance of public fund index enhancement products, including CSI 300, CSI 500, CSI 1000, and CSI A500 enhancement products, with metrics such as excess returns over different periods[28][32][35][37][39]