Market Performance - The recent five trading days saw the Sci-Tech 50 Index increase by 3.17%, the ChiNext Index by 5.69%, the large-cap value by 1.52%, the large-cap growth by 2.61%, the SSE 50 by 1.27%, and the small-cap represented by the CSI 2000 by 4.94% [1] - The sectors showing strong performance include computers and national defense, while oil, petrochemicals, and food and beverages lagged behind [1] Risk Premium Analysis - The risk premium, calculated as the inverse of the static PE of the CSI All Index minus the yield of ten-year government bonds, indicates that the implied returns of equity and bond assets are at historically high levels, reaching 4.17% on April 26, 2022, and 4.08% on October 28, 2022 [1] - As of January 19, 2024, the indicator stood at 4.11%, marking the fifth occurrence since 2016 to exceed 4% [1] Valuation Levels - As of June 27, 2025, the CSI All Index's PETTM percentile is at 59%, with the SSE 50 and CSI 300 at 66% and 57% respectively, while the ChiNext Index is close to 19% [2] - The ChiNext Index's valuation is relatively low compared to historical averages [2] Long-term Market Trends - The technical analysis of the Deep 100 Index suggests a cyclical pattern of bear markets every three years, followed by bull markets, with significant declines observed in previous cycles [2] - The current adjustment phase, which began in Q1 2021, appears to have sufficient time and space for a potential upward cycle [2] Fund Flow and Trading Activity - In the last five trading days, ETF funds experienced an outflow of 1.3 billion yuan, while margin trading increased by approximately 17 billion yuan, with an average daily trading volume of 1.4528 trillion yuan across the two markets [4] AI and Machine Learning Applications - The use of convolutional neural networks (CNN) for modeling price and volume data has been explored, with the latest focus on sectors such as banking and artificial intelligence [3][11]

- Model Name: Short-term Quantitative Timing Model; Model Construction Idea: The model is based on market sentiment indicators, valuation, macro liquidity, and macro fundamentals to generate timing signals; Model Construction Process: The model uses various indicators such as manufacturing PMI, long-term loan balance growth rate, M1 growth rate, PE and PB valuation percentiles, Beta dispersion, volume sentiment score, volatility, monetary rate, exchange rate expectation, and net financing amount to generate signals. For example, the formula for the volume sentiment score is: $$ \text{Volume Sentiment Score} = \frac{\text{Current Volume} - \text{Mean Volume}}{\text{Standard Deviation of Volume}} $$ where the current volume is the trading volume of the current period, the mean volume is the average trading volume over a specified period, and the standard deviation of volume is the standard deviation of trading volumes over the same period. The model evaluates these indicators to determine the overall market sentiment and generates a timing signal accordingly[9][14][15]; Model Evaluation: The model is highly sensitive to market sentiment indicators, which can lead to frequent signal changes[9] - Model Name: Growth-Value Style Rotation Model; Model Construction Idea: The model uses economic cycle analysis to determine the allocation between growth and value styles; Model Construction Process: The model evaluates the slope of the profit cycle, the level of the interest rate cycle, and the changes in the credit cycle. For example, the formula for the profit cycle slope is: $$ \text{Profit Cycle Slope} = \frac{\text{Current Profit} - \text{Previous Profit}}{\text{Previous Profit}} $$ where the current profit is the profit of the current period, and the previous profit is the profit of the previous period. The model also considers PE and PB valuation differences and turnover and volatility differences between growth and value styles to generate allocation signals[25][26]; Model Evaluation: The model provides significant improvement over the benchmark in terms of annualized returns and Sharpe ratio[25][26] - Model Name: Small-Cap vs. Large-Cap Style Rotation Model; Model Construction Idea: The model uses economic cycle analysis to determine the allocation between small-cap and large-cap styles; Model Construction Process: The model evaluates the slope of the profit cycle, the level of the interest rate cycle, and the changes in the credit cycle. For example, the formula for the interest rate cycle level is: $$ \text{Interest Rate Cycle Level} = \frac{\text{Current Interest Rate} - \text{Mean Interest Rate}}{\text{Standard Deviation of Interest Rate}} $$ where the current interest rate is the interest rate of the current period, the mean interest rate is the average interest rate over a specified period, and the standard deviation of interest rate is the standard deviation of interest rates over the same period. The model also considers PE and PB valuation differences and turnover and volatility differences between small-cap and large-cap styles to generate allocation signals[30][31][32]; Model Evaluation: The model provides significant improvement over the benchmark in terms of annualized returns and Sharpe ratio[30][31][32] - Model Name: Four-Style Rotation Model; Model Construction Idea: The model combines the conclusions of the growth-value and small-cap vs. large-cap rotation models to determine the allocation among four styles: small-cap growth, small-cap value, large-cap growth, and large-cap value; Model Construction Process: The model uses the signals generated by the growth-value and small-cap vs. large-cap rotation models to allocate the portfolio among the four styles. For example, if the growth-value model suggests overweighting value and the small-cap vs. large-cap model suggests overweighting large-cap, the allocation would be adjusted accordingly[33][34]; Model Evaluation: The model provides significant improvement over the benchmark in terms of annualized returns and Sharpe ratio[33][34] Model Backtest Results - Short-term Quantitative Timing Model: Annualized Return 16.24%, Annualized Volatility 14.70%, Maximum Drawdown 27.70%, Sharpe Ratio 0.9613, IR 0.5862, Monthly Win Rate 68.21%, Quarterly Win Rate 68.63%, Annual Win Rate 85.71%[16][19][22] - Growth-Value Style Rotation Model: Annualized Return 11.51%, Annualized Volatility 20.85%, Maximum Drawdown 43.07%, Sharpe Ratio 0.5316, IR 0.2672, Monthly Win Rate 58.00%, Quarterly Win Rate 60.00%, Annual Win Rate 85.71%[27][29] - Small-Cap vs. Large-Cap Style Rotation Model: Annualized Return 11.92%, Annualized Volatility 22.75%, Maximum Drawdown 50.65%, Sharpe Ratio 0.5283, IR 0.2386, Monthly Win Rate 60.67%, Quarterly Win Rate 56.00%, Annual Win Rate 85.71%[32] - Four-Style Rotation Model: Annualized Return 13.03%, Annualized Volatility 21.60%, Maximum Drawdown 47.91%, Sharpe Ratio 0.5834, IR 0.2719, Monthly Win Rate 59.33%, Quarterly Win Rate 62.00%, Annual Win Rate 85.71%[34][35]

Core Viewpoint - The market is expected to continue its oscillating trend in the upcoming week due to weak market sentiment and technical indicators suggesting a downward trend [1][2]. Market Overview - The liquidity shock indicator for the CSI 300 index was 1.23, indicating current market liquidity is 1.23 times higher than the average level over the past year [2]. - The PUT-CALL ratio for the SSE 50 ETF options increased to 1.06, reflecting a growing caution among investors regarding the short-term performance of the SSE 50 ETF [2]. - The five-day average turnover rates for the SSE Composite Index and Wind All A were 0.81% and 1.37%, respectively, indicating a decrease in trading activity [2]. Macroeconomic Factors - The onshore and offshore RMB exchange rates experienced slight fluctuations, with weekly changes of -0.03% and 0.14%, respectively [2]. - Recent economic data from the National Bureau of Statistics showed that in May, the industrial added value for large-scale enterprises grew by 5.8% year-on-year, and retail sales of consumer goods increased by 6.4% [2]. - Fixed asset investment for the first five months of the year rose by 3.7% year-on-year, with high-tech manufacturing and digital economy sectors showing significant growth [2]. Technical Analysis - The Wind All A index broke below the SAR point on June 19, indicating a bearish trend [2]. - The market score based on the moving average strength index is currently at 102, which is at the 39.7% percentile since 2021 [2]. - The sentiment model scored 1 out of 5, indicating weak market sentiment, while the trend model signal is positive and the weighted model signal is negative [2]. Market Performance - For the week of June 16-20, the SSE 50 index fell by 0.1%, the CSI 300 index decreased by 0.45%, the CSI 500 index dropped by 1.75%, and the ChiNext index declined by 1.66% [3]. - The overall market PE (TTM) stands at 19.2 times, which is at the 52.3% percentile since 2005 [3]. Factor Observations - The crowding degree for small-cap factors has decreased, with a current score of 0.79 for small-cap factors, -0.14 for low valuation factors, -0.11 for high profitability factors, and 0.00 for high profitability growth factors [3]. - The industry crowding degree is relatively high for sectors such as comprehensive, environmental protection, machinery equipment, banking, and non-ferrous metals, with notable increases in banking and medical biotechnology sectors [3].

2025 年 06 月 22 日 模型提示价量匹配度降低，市场情 绪回落较快 ——量化择时周报 20250620 证券分析师 王小心 A0230524100006 wangxx2@swsresearch.com 邓虎 A0230520070003 denghu@swsresearch.com 沈思逸 A0230521070001 shensy@swsresearch.com 联系人 王小心 (8621)23297818× wangxx2@swsresearch.com 本研究报告仅通过邮件提供给 中庚基金 使用。1 权 益 量 化 研 究 证 券 研 究 报 告 请务必仔细阅读正文之后的各项信息披露与声明 量 化 策 略 ⚫ 市场情绪进一步下行：市场情绪指标数值为 0.05，较上周五的 0.8 进一步下行，代表市 场情绪进一步回落，观点偏空。 ⚫ 价量匹配度降低，市场情绪继续下行：价量一致性（匹配度）降低代表当前资金活跃度欠 缺，资金观点分歧加剧、短期情绪不确定性增强；行业涨跌趋势指标继续提示行业涨跌趋 势较弱，指标位置虽略有提升但与本周行业普跌，少数上涨有关，因此我们不认为趋势方 面有显著改善。另外 PCR ...

Quantitative Models and Construction Methods - **Model Name**: TWO BETA Model **Model Construction Idea**: This model is designed to identify and recommend sectors or themes with strong momentum, focusing on technology-related sectors and specific themes like military and Hong Kong automotive industries[2][3][10]. **Model Construction Process**: The report does not provide detailed steps or formulas for the construction of the TWO BETA model. However, it is used to track and recommend sectors based on their relative performance and momentum trends[2][3][10]. **Model Evaluation**: The model continues to recommend technology sectors, military themes, and Hong Kong automotive themes, indicating its focus on identifying upward trends in these areas[2][3][10]. - **Model Name**: Industry Allocation Model **Model Construction Idea**: This model aims to recommend sectors based on medium-term perspectives, focusing on sectors undergoing a turnaround or showing resilience in current market conditions[2][3][10]. **Model Construction Process**: The report does not provide detailed steps or formulas for the construction of the industry allocation model. It is used to identify sectors like innovative drugs in Hong Kong, new consumption themes, and financial sectors in Hong Kong[2][3][10]. **Model Evaluation**: The model highlights sectors with potential for recovery or sustained growth, such as Hong Kong innovative drugs, new consumption, and financial sectors, which are deemed to have intact trends[2][3][10]. - **Model Name**: Timing System **Model Construction Idea**: This model uses the distance between short-term and long-term moving averages to determine the market's overall environment and timing signals[1][9][13]. **Model Construction Process**: 1. Define the short-term moving average (20-day) and long-term moving average (120-day) for the Wind All A Index. 2. Calculate the distance between the two moving averages: $ \text{Distance} = \frac{\text{Short-term MA} - \text{Long-term MA}}{\text{Long-term MA}} $ - Short-term MA (20-day): 5130 - Long-term MA (120-day): 5075 - Distance: 1.09% 3. Interpret the signal: If the absolute value of the distance is less than 3%, the market is considered to be in a consolidation phase[1][9][13]. **Model Evaluation**: The model indicates that the market remains in a consolidation phase, with the short-term moving average above the long-term moving average, suggesting a lack of strong directional trends[1][9][13]. Backtesting Results of Models - **TWO BETA Model**: No specific backtesting results or quantitative metrics are provided in the report[2][3][10]. - **Industry Allocation Model**: No specific backtesting results or quantitative metrics are provided in the report[2][3][10]. - **Timing System**: - Short-term MA: 5130 - Long-term MA: 5075 - Distance: 1.09% - Absolute distance remains below 3%, confirming the market's consolidation phase[1][9][13]. Quantitative Factors and Construction Methods - **Factor Name**: None explicitly mentioned in the report. Backtesting Results of Factors - **Factors**: No specific factors or their backtesting results are provided in the report.

Core Viewpoint - The market is expected to remain in a volatile trend next week, influenced by global events and technical indicators [1][2]. Market Overview - The liquidity shock indicator for the CSI 300 index was 0.74, indicating higher liquidity compared to the average level over the past year [2]. - The PUT-CALL ratio for the SSE 50 ETF options increased to 0.99, reflecting growing caution among investors regarding short-term trends [2]. - The five-day average turnover rates for the SSE Composite Index and Wind All A Index were 0.94% and 1.57%, respectively, showing increased trading activity [2]. Macroeconomic Factors - The onshore and offshore RMB exchange rates experienced slight fluctuations, with weekly changes of 0.05% and -0.02% respectively [2]. - China's May CPI was -0.1%, consistent with the previous value and above the Wind consensus expectation of -0.17% [2]. - The PPI for May was -3.3%, lower than the previous value of -2.7% and the Wind consensus expectation of -3.17% [2]. - New RMB loans in May amounted to 620 billion, below the Wind consensus expectation of 802.65 billion but higher than the previous value of 280 billion [2]. - M2 growth was 7.9%, below both the Wind consensus expectation of 8.08% and the previous value of 8% [2]. Technical Analysis - The Wind All A Index broke above the SAR reversal point on June 4 [2]. - The market score based on the moving average strength index is currently at 155, which is at the 61.5% percentile since 2021 [2]. - The A-share market showed a pattern of rising and then declining, with global markets reacting negatively to the outbreak of conflict in the Middle East [2]. Performance Summary - For the week of June 9-13, the SSE 50 Index fell by 0.46%, the CSI 300 Index decreased by 0.25%, and the CSI 500 Index dropped by 0.38%, while the ChiNext Index rose by 0.22% [3]. - The overall market PE (TTM) stands at 19.3 times, at the 53.5% percentile since 2005 [3]. Factor and Industry Analysis - The small-cap factor's congestion level continues to rise, currently at 1.13, while low valuation and high profitability factors show negative congestion levels [3]. - Industries with relatively high congestion levels include machinery, comprehensive services, environmental protection, non-ferrous metals, and beauty care [3]. - The congestion level for the medical biotechnology and beauty care sectors has increased significantly [3].

Market Performance - The Sci-Tech 50 Index decreased by 1.89% over the last five trading days, while the ChiNext Index increased by 0.22%. The large-cap value index rose by 0.10%, and the large-cap growth index fell by 0.16%. The Shanghai Stock Exchange 50 Index declined by 0.46%, and the small-cap index represented by the CSI 2000 dropped by 0.74%. The non-ferrous metals and oil & petrochemical sectors performed well, whereas household appliances and food & beverage sectors lagged behind [1]. Risk Premium Analysis - The static PE of the CSI All Index minus the yield of 10-year government bonds indicates a risk premium. Historical extreme bottoms have shown this data to be at two standard deviations above the mean, with notable instances in 2012, 2018, and 2020. As of April 26, 2022, the risk premium reached 4.17%, and on October 28, 2022, it rose to 4.08%. The latest reading on January 19, 2024, was 4.11%, marking the fifth instance since 2016 exceeding 4%. As of June 13, 2025, the indicator was at 3.83%, with the two standard deviation boundary at 4.75% [1]. Valuation Levels - As of June 13, 2025, the CSI All Index's PE TTM percentile was at 54%. The Shanghai Stock Exchange 50 and CSI 300 had percentiles of 62% and 52%, respectively. The ChiNext Index was close to 13%, while the CSI 500 and CSI 1000 were at 30% and 22%, respectively. The ChiNext Index's valuation is relatively low compared to historical averages [2]. Long-term Market Trends - The technical analysis of the Deep 100 Index indicates a bear market every three years, followed by a bull market. Historical declines ranged from 40% to 45%, with the current adjustment starting in Q1 2021 showing sufficient time and space for a potential upward cycle [2]. Fund Flow and Trading Activity - In the last five trading days, ETF funds saw an outflow of 17 billion yuan, while margin trading increased by approximately 9.4 billion yuan. The average daily trading volume across both markets was 1.3392 trillion yuan [2]. AI and Machine Learning Insights - A convolutional neural network (CNN) was utilized to model price and volume data, mapping learned features to industry themes. The latest recommended themes include non-ferrous metals and banking sectors [7].

Market Performance - The Sci-Tech 50 Index decreased by 1.89% over the last five trading days, while the ChiNext Index increased by 0.22%. The large-cap value index rose by 0.10%, and the large-cap growth index fell by 0.16%. The Shanghai 50 Index declined by 0.46%, and the small-cap index represented by the CSI 2000 dropped by 0.74%. The non-ferrous metals and oil & petrochemical sectors performed well, whereas household appliances and food & beverage sectors lagged behind [1]. Risk Premium Analysis - The static PE of the CSI All Index minus the yield of 10-year government bonds indicates a risk premium. Historical extreme bottoms have shown this data to be at two standard deviations above the mean, with notable peaks in 2012, 2018, and 2020. As of April 26, 2022, the risk premium reached 4.17%, and on October 28, 2022, it rose to 4.08%. The latest reading on January 19, 2024, was 4.11%, marking the fifth instance since 2016 exceeding 4%. As of June 13, 2025, the indicator was at 3.83%, with the two standard deviation boundary at 4.75% [1]. Valuation Levels - As of June 13, 2025, the CSI All Index's P/E TTM percentile was at 54%. The Shanghai 50 and CSI 300 indices were at 62% and 52%, respectively. The ChiNext Index was close to 13%, while the CSI 500 and CSI 1000 indices were at 30% and 22%. The ChiNext Index's valuation is relatively low compared to historical averages [2]. Long-term Market Trends - The technical analysis of the Deep 100 Index indicates a bear market every three years, followed by a bull market. Historical declines ranged from 40% to 45%, with the current adjustment starting in Q1 2021 showing sufficient time and space for a potential upward cycle [2]. Fund Flow and Trading Activity - Over the last five trading days, ETF funds saw an outflow of 17 billion yuan, while margin financing increased by approximately 9.4 billion yuan. The average daily trading volume across both markets was 1.3392 trillion yuan [2]. Neural Network Analysis - A convolutional neural network (CNN) was utilized to model price and volume data, mapping learned features to industry themes. The latest recommended themes include non-ferrous metals and banking sectors [9].

Group 1 - Market sentiment indicator decreased to 0.8, down from 1.75, indicating a bearish outlook [10][4] - Price-volume consistency improved, but industry trends remain weak with significant capital rotation [14][4] - Total A-share trading volume increased to 1.50 trillion RMB, with daily trading volume reaching 122.514 billion shares [17][4] Group 2 - Small-cap value style is currently favored, with a notable increase in short-term trend scores for sectors like social services, non-ferrous metals, and steel [32][34] - Social services sector saw a significant short-term trend score increase of 31.25% [32][34] - The model indicates a weakening differentiation between growth and value styles, suggesting a prevailing value preference [36][37]

金融工程 | 金工定期报告 金融工程 证券研究报告 2025 年 06 月 15 日 量化择时周报：仍处震荡上沿，维持中性仓位 仍处震荡上沿，维持中性仓位 上周周报(20250608)认为：短期市场宏观不确定性增加和指数在震荡格局 上沿位置的压制下，风险偏好较难快速提升，继续维持中性仓位。最终 wind 全 A 全周表现先扬后抑，微跌 0.27%。市值维度上，上周代表小市值股票 的中证 2000 下跌 0.75%，中盘股中证 500 下跌 0.38%，沪深 300 下跌 0.25%， 上证 50 下跌 0.46%;上周中信一级行业中，表现较强行业包括有色金属、石 油石化，有色金属上涨 3.95%，食品饮料、计算机表现较弱，食品饮料下跌 4.42%。上周成交活跃度上，石油石化和非银金融资金流入明显。 市场处于震荡格局，核心观测是市场风险偏好的变化。宏观方面，中东战 争对全球的资本市场的风险偏好带来压力；同时本周即将迎来美联储议息 的关键窗口期，市场的风险偏好也会承压；之前预告的陆家嘴论坛的利好 也在本周迎来明牌，或将利好兑现；技术指标上，wind 全 A 指数虽然上周 小幅回落，但仍位于震荡格局的上沿，如果没有 ...