Quantitative Models and Construction Methods - **Model Name**: Maximized Factor Exposure Portfolio (MFE) **Model Construction Idea**: The model aims to maximize single-factor exposure while controlling for various constraints such as industry exposure, style exposure, stock weight deviation, and turnover rate. This approach tests the effectiveness of factors under real-world constraints, ensuring their predictive power in portfolio construction [39][40][41] **Model Construction Process**: The optimization model is formulated 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} $ - **Objective Function**: Maximize single-factor exposure, where $f$ represents factor values, and $f^{T}w$ is the weighted exposure of the portfolio to the factor. $w$ is the stock weight vector to be optimized. - **Constraints**: - **Style Exposure**: $X$ is the matrix of stock exposures to style factors, $w_b$ is the benchmark weight vector, and $s_l$, $s_h$ are the lower and upper bounds for style factor exposure deviation. - **Industry Exposure**: $H$ is the industry exposure matrix, $h_l$, $h_h$ are the lower and upper bounds for industry deviation. - **Stock Weight Deviation**: $w_l$, $w_h$ are the lower and upper bounds for individual stock weight deviation. - **Component Weight Control**: $B_b$ is a binary vector indicating whether a stock belongs to the benchmark index, $b_l$, $b_h$ are the lower and upper bounds for component stock weight. - **No Short Selling**: Ensures non-negative weights and limits individual stock weights. - **Full Investment**: Ensures the portfolio is fully invested with weights summing to 1 [39][40][41] **Model Evaluation**: The model effectively tests factor validity under real-world constraints, ensuring factors contribute to portfolio returns in practical scenarios [39][40][41] Factor Construction and Methods - **Factor Name**: Standardized Unexpected Earnings (SUE) **Factor Construction Idea**: Measures the deviation of actual quarterly net profit from expected net profit, standardized by the standard deviation of expected net profit [17] **Factor Construction Process**: $ SUE = \frac{\text{Actual Quarterly Net Profit} - \text{Expected Net Profit}}{\text{Standard Deviation of Expected Net Profit}} $ **Factor Evaluation**: Useful for identifying stocks with earnings surprises, which may lead to price adjustments [17] - **Factor Name**: One-Month Reversal **Factor Construction Idea**: Captures short-term price reversal by measuring the return over the past 20 trading days [17] **Factor Construction Process**: $ \text{One-Month Reversal} = \text{Return over the past 20 trading days} $ **Factor Evaluation**: Effective in detecting short-term mean-reverting behavior in stock prices [17] - **Factor Name**: Delta ROA **Factor Construction Idea**: Measures the change in return on assets (ROA) compared to the same quarter of the previous year [17] **Factor Construction Process**: $ \Delta ROA = \text{Current Quarter ROA} - \text{ROA of the Same Quarter Last Year} $ **Factor Evaluation**: Indicates improvement or deterioration in asset efficiency, which can signal fundamental changes [17] Factor Backtesting Results **Performance in CSI 300 Sample Space** - **Standardized Unexpected Earnings**: Weekly excess return 1.35%, monthly excess return 3.78%, annual excess return 8.35% [19] - **One-Year Momentum**: Weekly excess return 1.27%, monthly excess return 1.98%, annual excess return -1.17% [19] - **Single-Quarter Revenue Growth**: Weekly excess return 1.08%, monthly excess return 3.86%, annual excess return 11.82% [19] **Performance in CSI 500 Sample Space** - **EPTTM Year Percentile**: Weekly excess return 1.69%, monthly excess return 1.74%, annual excess return 3.77% [21] - **Delta ROA**: Weekly excess return 1.00%, monthly excess return 2.43%, annual excess return 9.72% [21] - **Standardized Unexpected Earnings**: Weekly excess return 0.87%, monthly excess return 3.32%, annual excess return 7.87% [21] **Performance in CSI 1000 Sample Space** - **Standardized Unexpected Earnings**: Weekly excess return 0.75%, monthly excess return 3.69%, annual excess return 7.64% [23] - **Three-Month Reversal**: Weekly excess return 1.34%, monthly excess return 0.24%, annual excess return 5.36% [23] - **Single-Quarter Revenue Growth**: Weekly excess return 1.43%, monthly excess return 4.58%, annual excess return 11.12% [23] **Performance in CSI A500 Sample Space** - **Single-Quarter Revenue Growth**: Weekly excess return 1.43%, monthly excess return 4.58%, annual excess return 11.12% [25] - **Delta ROA**: Weekly excess return 0.63%, monthly excess return 4.33%, annual excess return 10.97% [25] - **Three-Month Reversal**: Weekly excess return 1.34%, monthly excess return 0.24%, annual excess return 5.36% [25] **Performance in Public Fund Heavy Index Sample Space** - **One-Year Momentum**: Weekly excess return 1.11%, monthly excess return 3.36%, annual excess return 1.15% [27] - **Delta ROA**: Weekly excess return 0.63%, monthly excess return 4.33%, annual excess return 10.97% [27] - **Standardized Unexpected Earnings**: Weekly excess return 0.75%, monthly excess return 3.69%, annual excess return 7.64% [27]

- The report tracks the performance of Guosen JinGong's index enhancement portfolios and public fund index enhancement products, as well as monitors the performance of common stock selection factors across different sample spaces[11][12][15] - Guosen JinGong's index enhancement portfolios are constructed based on three main components: return prediction, risk control, and portfolio optimization. These portfolios are benchmarked against indices such as CSI 300, CSI 500, CSI 1000, and CSI A500[12][14] - The report introduces the concept of Maximized Factor Exposure (MFE) portfolios to test the effectiveness of single factors under real-world constraints. The optimization model maximizes single-factor exposure while controlling for style, industry, stock weight deviations, and other constraints[41][42][43] - The optimization model for MFE portfolios is expressed as: $\begin{array}{ll}max&f^{T}\ w\\ s.t.&s_{l}\leq X(w-w_{b})\leq s_{h}\\ &h_{l}\leq H(w-w_{b})\leq h_{h}\\ &w_{l}\leq w-w_{b}\leq w_{h}\\ &b_{l}\leq B_{b}w\leq b_{h}\\ &\mathbf{0}\leq w\leq l\\ &\mathbf{1}^{T}\ w=1\end{array}$ where `f` represents factor values, `w` is the stock weight vector, and constraints include style exposure, industry exposure, stock weight deviations, and component stock weight limits[41][42] - The report tracks the performance of single-factor MFE portfolios across different sample spaces, including CSI 300, CSI 500, CSI 1000, CSI A500, and public fund heavy positions index. Factors are evaluated based on their excess returns relative to benchmarks[15][18][26] - Common stock selection factors are categorized into valuation, reversal, growth, profitability, liquidity, company governance, and analyst dimensions. Examples include BP (Book-to-Price), ROA (Return on Assets), and one-year momentum[16][17] - In the CSI 300 sample space, factors such as single-season ROA, standardized unexpected income, and standardized unexpected earnings performed well recently, while factors like one-month volatility and three-month volatility performed poorly[19] - In the CSI 500 sample space, factors such as one-year momentum and standardized unexpected earnings showed strong performance recently, while factors like one-month turnover and three-month volatility underperformed[21] - In the CSI 1000 sample space, factors such as one-year momentum and standardized unexpected earnings performed well recently, while factors like BP and single-season SP (Sales-to-Price) performed poorly[23] - In the CSI A500 sample space, factors such as DELTAROA (Change in ROA) and standardized unexpected income performed well recently, while factors like three-month volatility and one-month turnover performed poorly[25] - In the public fund heavy positions index sample space, factors such as one-year momentum and DELTAROA performed well recently, while factors like one-month turnover and three-month turnover underperformed[27] - Public fund index enhancement products are tracked for their excess returns relative to benchmarks. For CSI 300 products, recent weekly excess returns ranged from -1.41% to 1.91%, with a median of -0.09%[32] - For CSI 500 products, recent weekly excess returns ranged from -2.05% to 0.52%, with a median of -0.51%[34] - For CSI 1000 products, recent weekly excess returns ranged from -1.70% to 0.94%, with a median of -0.53%[37] - For CSI A500 products, recent weekly excess returns ranged from -1.10% to 0.71%, with a median of -0.25%[40]