金融工程 证 券 研 究 报 告 【金工周报】（20260224-20260227） 短期模型以中性为主，后市或维持中性震荡 本周回顾 本周市场普遍上涨，上证指数单周上涨 1.98%，创业板指单周上涨 1.05%。 A 股模型： 短期：成交量模型中性。特征龙虎榜机构模型中性。特征成交量模型看空。智 能算法沪深 300 模型中性，智能算法中证 500 模型中性。 中期：涨跌停模型中性。上下行收益差模型绝大部分宽基指数看多。月历效应 模型中性。 长期：长期动量模型中性。 综合：A 股综合兵器 V3 模型看空。A 股综合国证 2000 模型看空。 港股模型： 中期：成交额倒波幅模型看空。上下行收益差模型中性，上下行收益差相似模 型看多。 本周行业指数普遍上涨，涨幅前五的行业为：钢铁、有色金属、基础化工、煤 炭、电力及公用事业，跌幅前五的行业为：传媒、消费者服务、食品饮料、非 银行金融、银行。从资金流向角度来说，有色金属、石油石化、银行、农林牧 渔主力资金净流入居前，传媒、电力设备及新能源、计算机、机械、基础化工 主力资金净流出居前。 本周股票型基金总仓位为 95.75%，相较于上周增加了 24 个 bps，混合型基 ...

2026 年 2 月 28 日 总量研究 Beta 因子表现良好，量化选股组合超额收益显著 ——量化组合跟踪周报 20260228 要点 量化市场跟踪 大类因子表现：本周全市场股票池中，Beta 因子、盈利因子和流动性因子分别 获取正收益 1.04%、0.57%、0.55%；市值因子获取负收益-0.39%，市场表现为 小市值风格；其余风格因子表现一般。 单因子表现：沪深 300 股票池中，本周表现较好的因子有净利润断层 (4.93%)、 单季度 ROA (2.93%)、单季度 ROA 同比 (2.83%)。表现较差的因子有总资产毛 利率 TTM (-0.77%)、单季度总资产毛利率 (-0.66%)、经营现金流比率 (-0.66%)。 中证 500 股票池中，本周表现较好的因子有市净率因子 (0.83%)、市销率 TTM 倒数 (0.72%)、对数市值因子 (0.23%)。表现较差的因子有总资产毛利率 TTM (-3.84%)、毛利率 TTM (-3.51%)、单季度总资产毛利率 (-3.46%)。 流动性 1500 股票池中，本周表现较好的因子有 5 日反转 (0.76%)、净利润断层 (0.31%)、市净 ...

Quantitative Models and Construction Methods 1. **Model Name**: CSI 300 Enhanced Portfolio - **Model Construction Idea**: The model aims to achieve excess returns over the CSI 300 Index by leveraging quantitative strategies and factor-based stock selection - **Model Construction Process**: The model is constructed by selecting stocks from the CSI 300 Index based on specific quantitative factors and optimizing the portfolio to maximize excess returns while managing risk. The exact factors and optimization techniques are not detailed in the report - **Model Evaluation**: The model has shown consistent performance in generating excess returns over the CSI 300 Index in the year-to-date period[5][9][15] 2. **Model Name**: CSI 500 Enhanced Portfolio - **Model Construction Idea**: The model seeks to outperform the CSI 500 Index by utilizing quantitative strategies and factor-based stock selection - **Model Construction Process**: Stocks are selected from the CSI 500 Index based on quantitative factors, and the portfolio is optimized to achieve excess returns while controlling risk. Specific details of the factors and optimization are not provided in the report - **Model Evaluation**: The model's performance has been mixed, with negative excess returns in the year-to-date period[5][9][15] 3. **Model Name**: CSI 1000 Enhanced Portfolio - **Model Construction Idea**: The model aims to generate excess returns over the CSI 1000 Index through quantitative strategies and factor-based stock selection - **Model Construction Process**: Stocks are selected from the CSI 1000 Index using quantitative factors, and the portfolio is optimized to maximize excess returns while managing risk. Specific details of the factors and optimization are not provided in the report - **Model Evaluation**: The model has demonstrated positive excess returns in the year-to-date period[5][9][15] 4. **Model Name**: PB-Profit Combination Portfolio - **Model Construction Idea**: The portfolio combines price-to-book (PB) ratio and profitability factors to identify undervalued stocks with strong earnings potential - **Model Construction Process**: The portfolio is constructed by selecting stocks with low PB ratios and high profitability metrics. The exact methodology for combining these factors is not detailed in the report - **Model Evaluation**: The portfolio has shown strong performance, with significant positive excess returns over the CSI 300 Index in the year-to-date period[5][31][33] 5. **Model Name**: GARP Portfolio - **Model Construction Idea**: The portfolio follows the Growth at a Reasonable Price (GARP) strategy, focusing on stocks with a balance of growth and valuation metrics - **Model Construction Process**: Stocks are selected based on a combination of growth and valuation factors. The specific factors and their weights are not detailed in the report - **Model Evaluation**: The portfolio has achieved significant positive excess returns over the CSI 300 Index in the year-to-date period[5][35] 6. **Model Name**: Small-Cap Value Portfolio 1 - **Model Construction Idea**: The portfolio targets small-cap stocks with value characteristics, aiming to outperform the micro-cap index - **Model Construction Process**: Stocks are selected based on small-cap and value factors. The exact methodology for combining these factors is not detailed in the report - **Model Evaluation**: The portfolio has underperformed the micro-cap index in the year-to-date period[5][37] 7. **Model Name**: Small-Cap Value Portfolio 2 - **Model Construction Idea**: Similar to Small-Cap Value Portfolio 1, this portfolio focuses on small-cap stocks with value characteristics - **Model Construction Process**: Stocks are selected based on small-cap and value factors. The exact methodology for combining these factors is not detailed in the report - **Model Evaluation**: The portfolio has outperformed the micro-cap index in the year-to-date period[5][39] 8. **Model Name**: Small-Cap Growth Portfolio - **Model Construction Idea**: The portfolio targets small-cap stocks with growth characteristics, aiming to outperform the micro-cap index - **Model Construction Process**: Stocks are selected based on small-cap and growth factors. The exact methodology for combining these factors is not detailed in the report - **Model Evaluation**: The portfolio has underperformed the micro-cap index in the year-to-date period[5][41] --- Model Backtesting Results 1. **CSI 300 Enhanced Portfolio** - Weekly return: -0.39% - Weekly excess return: -0.47% - Year-to-date return: 6.85% - Year-to-date excess return: 5.20%[9][15] 2. **CSI 500 Enhanced Portfolio** - Weekly return: -1.74% - Weekly excess return: 0.82% - Year-to-date return: 11.11% - Year-to-date excess return: -1.01%[9][15] 3. **CSI 1000 Enhanced Portfolio** - Weekly return: -0.97% - Weekly excess return: 1.58% - Year-to-date return: 11.99% - Year-to-date excess return: 3.31%[9][15] 4. **PB-Profit Combination Portfolio** - Weekly return: 0.92% - Weekly excess return: 0.84% - Year-to-date return: 6.17% - Year-to-date excess return: 4.52%[31][33] 5. **GARP Portfolio** - Weekly return: 0.95% - Weekly excess return: 0.87% - Year-to-date return: 11.43% - Year-to-date excess return: 9.78%[35] 6. **Small-Cap Value Portfolio 1** - Weekly return: -2.44% - Weekly excess return: -1.29% - Year-to-date return: 7.89% - Year-to-date excess return: -2.83%[37] 7. **Small-Cap Value Portfolio 2** - Weekly return: -1.64% - Weekly excess return: -0.48% - Year-to-date return: 12.37% - Year-to-date excess return: 1.66%[39] 8. **Small-Cap Growth Portfolio** - Weekly return: -2.07% - Weekly excess return: -0.92% - Year-to-date return: 9.13% - Year-to-date excess return: -1.59%[41] --- Quantitative Factors and Construction Methods 1. **Factor Name**: Market Capitalization (Size) Factor - **Construction Idea**: Small-cap stocks tend to outperform large-cap stocks over time - **Construction Process**: Stocks are ranked by market capitalization, and the top 10% (smallest) and bottom 10% (largest) are selected to form long and short portfolios, respectively. The difference in returns between these portfolios represents the factor's performance - **Evaluation**: The factor has shown mixed performance across different indices and time periods[43][44][45] 2. **Factor Name**: Price-to-Book (PB) Factor - **Construction Idea**: Low PB stocks are expected to outperform high PB stocks - **Construction Process**: Stocks are ranked by PB ratio, and the top 10% (lowest PB) and bottom 10% (highest PB) are selected to form long and short portfolios, respectively. The difference in returns between these portfolios represents the factor's performance - **Evaluation**: The factor has shown strong performance in the short term but mixed results in the year-to-date period[43][44][45] 3. **Factor Name**: Price-to-Earnings (PE_TTM) Factor - **Construction Idea**: Low PE stocks are expected to outperform high PE stocks - **Construction Process**: Stocks are ranked by PE ratio, and the top 10% (lowest PE) and bottom 10% (highest PE) are selected to form long and short portfolios, respectively. The difference in returns between these portfolios represents the factor's performance - **Evaluation**: The factor has shown positive short-term performance but mixed year-to-date results[43][44][45] 4. **Factor Name**: Reversal Factor - **Construction Idea**: Stocks with recent underperformance are expected to outperform in the short term - **Construction Process**: Stocks are ranked by recent performance, and the top 10% (worst performers) and bottom 10% (best performers) are selected to form long and short portfolios, respectively. The difference in returns between these portfolios represents the factor's performance - **Evaluation**: The factor has shown positive short-term performance but negative year-to-date results[49][50] 5. **Factor Name**: Turnover Factor - **Construction Idea**: Stocks with lower turnover rates are expected to outperform those with higher turnover rates - **Construction Process**: Stocks are ranked by turnover rate, and the top 10% (lowest turnover) and bottom 10% (highest turnover) are selected to form long and short portfolios, respectively. The difference in returns between these portfolios represents the factor's performance - **Evaluation**: The factor has shown strong short-term performance but negative year-to-date results[49][50] 6. **Factor Name**: Volatility Factor - **Construction Idea**

Group 1: Market Overview - The Beta factor and valuation factor achieved positive returns of 0.66% and 0.48% respectively, while the market capitalization factor recorded a negative return of -0.80%, indicating a small-cap market performance [5] - The quant stock selection strategy yielded significant excess returns, with the PB-ROE-50 combination achieving excess returns of 1.38%, 2.54%, and 4.23% for the CSI 500, CSI 800, and the overall market respectively [5] Group 2: REITs Market - The secondary market prices of publicly listed REITs in China showed an upward trend, with the CSI REITs closing at 806.72 and the CSI REITs total return index at 1047.51, reflecting weekly returns of 2.09% and 2.17% respectively [5] - Compared to other major asset classes, the return rates ranked as follows: Gold > Convertible Bonds > REITs > A-shares > Crude Oil > Pure Bonds > US Stocks [5] Group 3: Banking Sector Insights - The 2025 annual report from the banking industry indicated an increase in the scale of wealth management products by nearly 3.3 trillion, achieving a year-on-year increase despite a high base [6] - "Fixed income +" wealth management products have become a significant growth point, while the average yield on wealth management products has dropped below 2% [6] - The proportion of wealth management products in deposit asset allocation rose to 28.2%, with the market share of wealth management companies exceeding 90% [6] Group 4: Copper Industry Analysis - The TC spot price reached a new low, indicating continued tightness in copper concentrate procurement, while cable manufacturers' operating rates increased week-on-week [8] - Despite the rise in copper prices, domestic social inventory continues to grow, which may suppress demand [8] - The outlook for 2026 remains optimistic with a tight supply-demand balance expected to support copper prices [8] Group 5: Chemical Industry Trends - The price of spandex has seen a significant increase of 1000 yuan/ton due to pressure from losses, marking a turning point in the spandex market [8] - Spandex prices have dropped from a historical high of 83,750 yuan/ton in 2021 to 23,600 yuan/ton in early January 2026, representing a decline of 72% [8]

Core Viewpoint - The report highlights the performance of various market factors and investment strategies, indicating a mixed performance across different stock pools and sectors, with certain factors yielding positive excess returns [4][7][8][9][10]. Group 1: Market Factor Performance - The overall market showed positive returns for the Beta factor (0.66%) and valuation factor (0.48%), while the market capitalization factor yielded negative returns (-0.80%), indicating a preference for small-cap stocks [4]. - In the CSI 300 stock pool, the best-performing factors included the 5-day average turnover rate (4.52%) and 5-day reversal (3.17%), while the total asset growth rate (-2.05%) and quarterly ROE (-1.16%) performed poorly [5]. - The CSI 500 stock pool saw strong performance from the 5-day reversal (3.80%) and quarterly operating profit growth rate (1.98%), but struggled with momentum-adjusted small caps (-2.41%) [5]. Group 2: Sector-Specific Factor Performance - Fundamental factors showed varied performance across sectors, with net asset per share and TTM operating profit factors performing well in the defense and leisure services sectors [6]. - Valuation factors such as BP and EP also yielded positive returns in the defense and leisure services industries, while residual volatility and liquidity factors performed well in the coal sector [6]. Group 3: Investment Strategy Performance - The PB-ROE-50 combination achieved positive excess returns across stock pools, with the CSI 500 pool gaining 1.38% and the CSI 800 pool gaining 2.54% [7]. - Public and private fund research selection strategies both generated positive excess returns, with public strategies outperforming the CSI 800 by 0.61% and private strategies by 3.43% [8]. - The block trading combination also achieved positive excess returns relative to the CSI All Index, with a gain of 0.86% [9]. - The targeted issuance combination outperformed the CSI All Index by 1.32%, indicating strong performance in this investment strategy [10].

- The Beta factor and valuation factor achieved positive returns of 0.66% and 0.48% respectively, while the size factor had a negative return of -0.80%[1][18] - In the CSI 300 stock pool, the best-performing factors this week were the 5-day average turnover rate (4.52%), 5-day reversal (3.17%), and price-to-book ratio factor (3.10%)[1][12] - In the CSI 500 stock pool, the best-performing factors this week were the 5-day reversal (3.80%), single-quarter operating profit growth rate (1.98%), and price-to-sales ratio TTM reciprocal (1.65%)[1][14] - In the liquidity 1500 stock pool, the best-performing factors this week were the post-morning return factor (2.18%), 5-day reversal (2.17%), and standardized unexpected income (1.77%)[2][16] - The PB-ROE-50 portfolio achieved positive excess returns in various stock pools this week, with excess returns of 1.38% in the CSI 500 stock pool, 2.54% in the CSI 800 stock pool, and 4.23% in the entire market stock pool[2][23] - The public research stock selection strategy and private research tracking strategy achieved positive excess returns this week, with the public research stock selection strategy achieving an excess return of 0.61% relative to the CSI 800, and the private research tracking strategy achieving an excess return of 3.43% relative to the CSI 800[3][25] - The block trading portfolio achieved a positive excess return of 0.86% relative to the CSI All Share Index this week[3][29] - The directed issuance portfolio achieved a positive excess return of 1.32% relative to the CSI All Share Index this week[3][35]

Core Viewpoint - The AI Fund Wanjiashengli Quantitative Stock Selection Mixed Initiation A (019987) reported a profit of 112,600 yuan in Q4 2025, with a weighted average profit per fund share of 0.0216 yuan, and a net value growth rate of 2.21% during the reporting period [3]. Fund Performance - As of January 21, the fund's unit net value was 1.047 yuan, with a one-year cumulative growth rate of 12.17%, ranking 622 out of 673 comparable funds [3][4]. - The fund's net value growth rate over the past three months was 0.24%, ranking 617 out of 689, and over the past six months, it was 5.07%, also ranking 617 out of 689 [4]. Investment Strategy - The fund manager emphasized restructuring the dividend stock pool based on the characteristics of dividend stocks, integrating high-frequency volume and price strategies to capture micro-structural market information [3]. - The fund utilizes efficient AI algorithms and robust hardware resources to analyze high-frequency market data, aiming to identify short-cycle predictive factors for stock selection [3]. Risk and Return Metrics - The fund's Sharpe ratio since inception is 0.2818, indicating a moderate risk-adjusted return [8]. - The maximum drawdown since inception is 20.86%, with the largest quarterly drawdown occurring in Q1 2024 at 16.34% [11]. Portfolio Composition - The fund maintains a high average stock position of 92.53% since inception, compared to the industry average of 84.04%, with a peak stock position of 93.54% at the end of Q3 2024 [14]. - As of Q4 2025, the fund's total assets amounted to 5.4297 million yuan [16]. Top Holdings - The top ten holdings of the fund include companies such as Luxi Chemical, China Ping An, CITIC Bank, Xiamen Xiangyu, Sinopec, Zhonggu Logistics, China Construction Bank, Hu Nong Commercial Bank, China Petroleum, and Pudong Development Bank [19].

Core Viewpoint - The AI Fund Zhongtai Dividend Quantitative Stock Selection A (021167) reported a profit of 349,400 yuan in Q4 2025, with a weighted average profit per fund share of 0.0311 yuan. The fund's net value growth rate for the reporting period was 2.76%, and the fund size reached 12.6287 million yuan by the end of Q4 2025 [3]. Fund Performance - As of January 22, the fund's unit net value was 1.148 yuan. The fund manager, Zou Wei, currently manages five funds. The Zhongtai CSI 500 Index Enhanced A had the highest one-year growth rate at 43.81%, while the Zhongtai Dividend Quantitative Stock Selection A had the lowest at 13.09% [3]. - The fund's performance over the past three months showed a growth rate of 0.96%, ranking 105 out of 121 comparable funds. Over the past six months, the growth rate was 4.90%, ranking 103 out of 121. The one-year growth rate was 13.09%, ranking 110 out of 119 [4]. Risk and Management - The fund's Sharpe ratio since inception is 0.748 [9]. The maximum drawdown since inception is 12.37%, with the largest quarterly drawdown occurring in Q2 2025 at 6.3% [11]. - The average stock position since inception is 90.65%, compared to the peer average of 88.34%. The fund reached a peak stock position of 92.43% at the end of H1 2025 and a low of 85.08% at the end of Q3 2024 [13]. Fund Holdings - As of the end of Q4 2025, the fund's size was 12.6287 million yuan. The top ten holdings are stable and include China Merchants Bank, China State Construction, Agricultural Bank of China, Midea Group, Kweichow Moutai, Chengdu Bank, China National Offshore Oil Corporation, Hisense Visual Technology, Nanjing Steel, and Industrial and Commercial Bank of China [16][19].

Core Viewpoint - The AI Fund, CITIC Prudential State-Owned Enterprise Dividend Quantitative Stock A, reported a profit of 132,700 yuan for Q4 2025, with a weighted average profit per fund share of 0.0284 yuan, and a net asset value growth rate of 1.97% during the reporting period [3]. Fund Performance - As of January 21, the fund's unit net value was 1.091 yuan, with a fund size of 4.8765 million yuan [3][18]. - The fund's performance over the past three months showed a return of -2.22%, ranking 115 out of 121 comparable funds; over the past six months, it returned -1.66%, ranking 117 out of 121; and over the past year, it achieved a return of 6.31%, ranking 115 out of 119 [4]. Investment Strategy - The fund maintained a high stock position during the reporting period, focusing on investment opportunities in high-dividend state-owned enterprises, and employed a quantitative stock selection model to strive for long-term returns exceeding the performance benchmark [3]. Risk Metrics - The fund's Sharpe ratio since inception is 0.5564, indicating a moderate risk-adjusted return [9]. - The maximum drawdown since inception is 12.44%, with the largest quarterly drawdown occurring in Q2 2025 at 6.09% [13]. Portfolio Composition - The average stock position since inception has been 88.66%, slightly above the peer average of 88.34%. The fund reached a peak stock position of 90.27% at the end of 2025, with a low of 83.8% at the end of Q3 2024 [16]. - As of Q4 2025, the top ten holdings of the fund include China Shenhua, Hengyuan Coal Power, China Construction Bank, Bank of Communications, Changsha Bank, Industrial and Commercial Bank of China, Jiangsu Jinzhong, Bohai Ferry, Jianfa Co., and Sheneng Co. [21].

Core Insights - The AI Fund, CITIC Prudential Dividend Navigation Quantitative Stock A (021983), reported a profit of 263,500 yuan for Q4 2025, with a weighted average profit per fund share of 0.0391 yuan. The fund's net value growth rate for the reporting period was 2.24%, and the fund size reached 5.9149 million yuan by the end of Q4 2025 [3][14]. Fund Performance - As of January 21, the fund's unit net value was 1.034 yuan. Over the past year, the fund achieved a net value growth rate of 5.41%, ranking 12th out of 13 comparable funds [3][4]. - The fund's performance over the last three months showed a net value growth rate of -0.87%, and over the last six months, it was -0.89%, both ranking 12th out of 13 in its category [4]. Investment Strategy - The fund maintains a high stock position, focusing on investment opportunities related to dividend themes. It employs a quantitative stock selection model to strive for long-term returns that exceed the performance benchmark [3]. Risk Metrics - The fund's maximum drawdown since inception is 7.02%, with the largest quarterly drawdown occurring in Q3 2025 at 5.5% [9]. Portfolio Composition - The average stock position since inception is 89.85%, slightly above the category average of 89.51%. The fund reached its highest stock position of 90.91% at the end of Q1 2025 and its lowest of 89.38% at the end of 2025 [13]. - As of Q4 2025, the top ten holdings of the fund include China Shenhua, Hengyuan Coal Power, Jizhong Energy, and several major banks [17].