微盘股指数周报：现阶段主要矛盾是交易范式之争-20250630

Quantitative Models and Construction Methods 1. Model Name: Diffusion Index Model - Model Construction Idea: The model is designed to monitor the critical points of trend changes in the diffusion index, which reflects the breadth of stock price movements within the micro-cap index constituents[5][40]. - Model Construction Process: The diffusion index is calculated based on the relative price changes of constituent stocks over a specific time window. For example, if all stocks in the micro-cap index drop by 5% after 5 days, the diffusion index value is 0.13. The formula is as follows: $ DI = \frac{\text{Number of stocks meeting criteria}}{\text{Total number of stocks}} $ The model uses three methods to generate signals: - Initial Threshold Method (Left-Side Trading): Triggered a sell signal on May 8, 2025, when the index reached 0.9850[43]. - Delayed Threshold Method (Right-Side Trading): Triggered a sell signal on May 15, 2025, at 0.8975[47]. - Dual Moving Average Method (Adaptive Trading): Triggered a sell signal on June 11, 2025[48]. - Model Evaluation: The model effectively identifies overbought conditions and provides timely sell signals, but its predictive power may be limited by the dynamic updates of index constituents[40][5]. --- Quantitative Factors and Construction Methods 1. Factor Name: Illiquidity Factor - Factor Construction Idea: Measures the illiquidity of stocks, which is inversely related to trading volume and price impact[4][35]. - Factor Construction Process: The factor is calculated as the ratio of absolute daily returns to trading volume over a specific period. $ Illiquidity = \frac{|R_t|}{Volume_t} $ - $R_t$: Daily return - $Volume_t$: Daily trading volume - Factor Evaluation: This factor showed the highest rank IC this week (0.174), significantly outperforming its historical average (0.038), indicating strong predictive power in the current market environment[4][35]. 2. Factor Name: 1-Year Volatility Factor - Factor Construction Idea: Captures the historical price volatility of stocks over the past year[4][35]. - Factor Construction Process: The factor is calculated as the standard deviation of daily returns over the past 252 trading days. $ Volatility = \sqrt{\frac{\sum_{i=1}^{252}(R_i - \bar{R})^2}{252}} $ - $R_i$: Daily return - $\bar{R}$: Average daily return - Factor Evaluation: This factor ranked second in rank IC this week (0.155), a significant improvement from its historical average (-0.033), suggesting its relevance in identifying outperforming stocks[4][35]. 3. Factor Name: Beta Factor - Factor Construction Idea: Measures the sensitivity of a stock's returns to market returns[4][35]. - Factor Construction Process: The factor is calculated using regression analysis: $ R_i = \alpha + \beta R_m + \epsilon $ - $R_i$: Stock return - $R_m$: Market return - $\beta$: Beta coefficient - Factor Evaluation: This factor ranked third in rank IC this week (0.146), outperforming its historical average (0.004), indicating its effectiveness in the current market[4][35]. 4. Factor Name: Free Float Ratio Factor - Factor Construction Idea: Represents the proportion of shares available for public trading relative to total shares outstanding[4][35]. - Factor Construction Process: $ Free\ Float\ Ratio = \frac{\text{Free Float Shares}}{\text{Total Shares Outstanding}} $ - Factor Evaluation: This factor ranked fourth in rank IC this week (0.113), significantly better than its historical average (-0.011), highlighting its predictive strength in the current market[4][35]. 5. Factor Name: Leverage Factor - Factor Construction Idea: Measures the financial leverage of a company, indicating its debt level relative to equity[4][35]. - Factor Construction Process: $ Leverage = \frac{\text{Total Debt}}{\text{Total Equity}} $ - Factor Evaluation: This factor ranked fifth in rank IC this week (0.031), slightly above its historical average (-0.005), showing moderate predictive power[4][35]. --- Backtesting Results of Factors Weekly Rank IC Performance 1. Illiquidity Factor: Weekly rank IC = 0.174, Historical average = 0.038[4][35] 2. 1-Year Volatility Factor: Weekly rank IC = 0.155, Historical average = -0.033[4][35] 3. Beta Factor: Weekly rank IC = 0.146, Historical average = 0.004[4][35] 4. Free Float Ratio Factor: Weekly rank IC = 0.113, Historical average = -0.011[4][35] 5. Leverage Factor: Weekly rank IC = 0.031, Historical average = -0.005[4][35] Weekly Rank IC Underperformance 1. Nonlinear Market Cap Factor: Weekly rank IC = -0.285, Historical average = -0.033[4][35] 2. Log Market Cap Factor: Weekly rank IC = -0.285, Historical average = -0.033[4][35] 3. 10-Day Return Factor: Weekly rank IC = -0.205, Historical average = -0.061[4][35] 4. 10-Day Free Float Turnover Factor: Weekly rank IC = -0.183, Historical average = -0.06[4][35] 5. 10-Day Total Market Cap Turnover Factor: Weekly rank IC = -0.16, Historical average = -0.059[4][35] --- Strategy Performance Small-Cap Low-Volatility 50 Strategy - Strategy Description: Selects 50 stocks with the smallest market capitalization and lowest volatility from the micro-cap index constituents, rebalanced biweekly[19][37]. - Performance: - 2024 Return: 7.07%, Excess Return: -2.93% - 2025 YTD Return: 53.93%, Weekly Excess Return: 0.38% - Benchmark: Wind Micro-Cap Index (8841431.WI) - Transaction Cost: 0.3% per side[19][37]