Group 1: Market Sentiment Indicators - The market sentiment index as of October 10 is 1.75, a slight decrease from 1.85 on September 26, indicating a bearish sentiment [8][11] - The financing balance ratio continues to rise, reflecting an increase in market leverage sentiment and improving trading atmosphere [27][11] - The industry trading volatility continues to decline, suggesting a slowdown in fund switching activity and a decrease in market participants' divergent views on short-term industry value [21][11] Group 2: Timing Model Insights - The model indicates a preference for small-cap value style, with a weak signal strength due to a slight decline in the 5-day RSI relative to the 20-day RSI [45][46] - The short-term trend scores for industries such as non-ferrous metals, power equipment, real estate, machinery, and electronics are notably strong, with non-ferrous metals scoring the highest at 98.31 [34][36] - The model maintains a strong signal for value style, suggesting potential for further strengthening in the future [45][46] Group 3: Industry Crowding and Performance - Recent high returns in non-ferrous metals and coal are accompanied by high fund crowding, indicating potential volatility risks due to valuation and sentiment corrections [42][41] - Industries like automotive and electronics show high crowding but lower returns, while sectors with low crowding such as pharmaceuticals and beauty care may present long-term investment opportunities as risk appetite increases [42][41] - The average crowding levels for industries as of October 10 show automotive, environmental protection, real estate, power equipment, and electronics as the highest, while agriculture, computers, defense, beauty care, and pharmaceuticals are the lowest [40][41]

Market Overview - Short-term market may experience adjustments due to high liquidity levels, with the liquidity shock indicator for the CSI 300 index at 1.36, lower than the previous week's 1.86, indicating current market liquidity is 1.36 times the average level over the past year [1] - The PUT-CALL ratio for the SSE 50 ETF has decreased to 0.85 from 0.91, suggesting reduced caution among investors regarding the short-term performance of the SSE 50 ETF [1] - The five-day average turnover rates for the SSE Composite Index and Wind All A are at 1.34% and 1.91%, respectively, maintaining trading activity levels consistent with the past [1] Macroeconomic Factors - The RMB exchange rate fluctuated last week, with onshore and offshore rates showing weekly declines of -0.06% and -0.17% respectively [1] - The official manufacturing PMI for China in September was reported at 49.8, slightly above the previous value of 49.4 but below the consensus expectation of 49.95; the S&P Global China Manufacturing PMI was at 51.2, up from 50.5 [1] Event-Driven Analysis - U.S. stock markets experienced significant declines, with the Dow Jones, S&P 500, and Nasdaq indices reporting weekly returns of -2.73%, -2.43%, and -2.53% respectively, influenced by strong statements from former President Trump regarding potential tariff increases on imports [2] - China's Ministry of Commerce announced the implementation of export control measures on certain rare earth items and technologies, adding 14 foreign entities to a list of unreliable entities [2] Technical Analysis - The Wind All A index broke above the SAR indicator on September 11, indicating a potential upward trend [3] - The market score based on the moving average strength index is currently at 198, placing it in the 71.9% percentile for 2023 [3] - The sentiment model score is at 2 out of 5, indicating weak market sentiment, while the trend model signal is positive and the weighted model signal is negative [3] - The A-share market showed a downward trend last week, with the SSE 50 index down 0.47%, CSI 300 down 0.51%, and the ChiNext index down 3.86% [3] Factor Crowding Observation - The crowding degree for small-cap factors continues to decline, with a score of 0.08; low valuation factors at -0.31; high profitability factors at -0.18; and high growth factors at 0.19 [4] - Industry crowding degrees are relatively high in sectors such as non-ferrous metals, power equipment, comprehensive, communication, and electronics, with non-ferrous metals and steel showing significant increases [4]

证券研究报告 | 金融工程 2025 年 10 月 12 日 短期扰动不改看好观点 ——A 股趋势与风格定量观察 20251012 1. 当前市场观察 ❑ 节后两日市场先涨后跌，成长风格明显回调，价值风格逆势上涨。具体来 看，万得全 A 指数下跌 0.36%，上证 50、沪深 300、中证 1000 分别下跌约 0.47%、0.51%、0.54%。国证价值上涨约 1.52%，而国证成长下跌约 1.41%，创业板指、科创 50 分别下跌约 3.85%、2.85%。 ❑ 择时观点上，10 月 10 日夜间中美摩擦再度升级，下周一权益市场大概率走 弱，不过从历史统计上来看，类似事件发生后 5 日内权益资产大概率会有所 修复，结合当前交易情绪仍偏强，我们认为短期扰动并不会改变前期对 A 股 市场震荡看好的观点。具体来看，我们统计了 2018 年以来包括中美贸易摩 擦、疫情、地缘冲突等事件发生当日、5 日、20 日内股、债、商、汇、权益 风格走势，可以发现利空事件发生当日 A 股、港股、美股均有较为明显的回 调（万得全 A 与恒生科技平均跌幅为 3.80%和 4.94%），顺周期的商品如铜 也会明显走低（平均跌幅 2. ...

Market Performance - The Sci-Tech 50 Index decreased by 1.48% over the last five trading days, while the ChiNext Index fell by 3.79%. In contrast, the large-cap value stocks rose by 1.03%, and the large-cap growth stocks declined by 0.67%. The Shanghai 50 Index increased by 1.13%, and the small-cap index represented by the CSI 2000 dropped by 0.15%. The sectors of non-ferrous metals and steel performed well, while media and communication lagged behind [1]. Risk Premium and Valuation Levels - As of October 10, 2025, the risk premium, calculated as the inverse of the static PE of the CSI All Share Index minus the yield of ten-year government bonds, stood at 2.84%. The two-standard-deviation boundary is 4.76%. The valuation levels indicate that the CSI All Share Index's PETTM is at the 80th percentile, with the Shanghai 50 and CSI 300 both at 71%. The ChiNext Index is close to the 50th percentile, while the CSI 500 and CSI 1000 are at 63% and 61%, respectively. The ChiNext Index's valuation is relatively at the historical median level [1]. ETF Fund Flows - In the last five trading days, ETF inflows amounted to 68.6 billion yuan, and the margin trading balance increased by approximately 15.3 billion yuan. The average daily trading volume across the two markets was 233.17 billion yuan [2]. Industry Focus - The latest thematic allocation focuses on semiconductor materials, chips, and information technology. This includes specific indices such as the CSI Semiconductor Industry Index, the Shanghai Stock Exchange Sci-Tech Board Semiconductor Materials Equipment Theme Index, the CSI Semiconductor Materials Equipment Index, the Shanghai Stock Exchange Sci-Tech Board Chip Index, and the Shanghai Stock Exchange Sci-Tech Board New Generation Information Technology Index [2][3]. Long-term Market Sentiment - The report includes observations on the proportion of stocks above the 200-day long-term moving average, indicating market sentiment trends [13]. Financing Balance - The report tracks the financing balance, which is a critical indicator of market liquidity and investor sentiment [16]. Individual Stock Performance - There is a statistical distribution of individual stocks based on their year-to-date performance across different return intervals, providing insights into stock performance trends [18]. Oversold Indices - The report highlights indices that are currently considered oversold, which may present potential investment opportunities [20].

Market Performance Review - The major stock indices showed a mixed performance in September, with growth style leading the way. As of September 26, the Shanghai Composite Index fell by 0.77%, while the Shenzhen Component Index rose by 4.04%, and the ChiNext Index increased by 9.04% [6][17] - The overall market index rose by 1.31%, with the mid-cap index up by 3.62% and the small-cap index down by 0.30%. The "茅" index increased by 3.25%, and the "宁" combination rose by 9.44% [6][17] - External disturbances were minimal, and the A-share market experienced a rebound after an initial decline following the September 3 military parade. The internal economic data remained stable, and the Federal Reserve's interest rate cut aligned with market expectations [6][17] A-Share High-Frequency Data Tracking - The dynamic HMM timing model indicated that the current market potential returns do not cover risks, leading to a recommendation for a reduced position [28] - The personal investor sentiment index showed a slight recovery, with a 7-day moving average of -4.56% as of September 27, significantly down from 15.96% on September 20 [33] - Financing sentiment has improved, maintaining a net inflow trend, with financing transactions accounting for over 20% of A-share trading volume [38] Future Outlook and Investment Views - The report suggests a "time for space" strategy, waiting for the next policy trigger. Since the market rally began on June 23, the A-share market has accumulated significant gains, and a technical stagnation is observed [7][46] - The expectation is that domestic economic policies will focus on implementing existing plans, with the "15th Five-Year Plan" policies anticipated to trigger the next market rally [7][46] - In terms of asset allocation, Hong Kong stocks are seen as having better value, and the report emphasizes the importance of identifying individual stocks with "turnaround" logic in the A-share market [8][46]

Core Insights - The report indicates that the market is in an upward trend, with the key observation variable being whether the market's profit effect can be sustained. As long as the profit effect remains positive, incremental funds are expected to continue entering the market [2][10][14] - The current WIND All A trend line is around 6184 points, with a profit effect of approximately 0.66%, still positive. It is advised to hold positions until the profit effect turns negative [2][10][14] - The industry allocation model suggests that the precious metals sector is still in an upward trend and should be monitored. Additionally, sectors benefiting from policy-driven initiatives, such as new energy and chemicals, are expected to perform well [2][10][14] Market Overview - The market is currently showing a profit effect of about 0.66%, indicating a positive environment for investment. The report suggests maintaining positions until the profit effect turns negative [2][10][14] - The valuation indicators for the WIND All A index show a PE at the 85th percentile and a PB at the 50th percentile, indicating a moderate valuation level [2][10][14] - The report recommends an 80% allocation to absolute return products based on the current market conditions and trends [2][10][14] Industry Focus - The report highlights the precious metals sector as a continuing upward trend, which should be closely monitored [2][10][14] - The technology sector, particularly chips and robotics, is recommended for continued focus based on the TWO BETA model [2][10][14] - Given the uncertainties surrounding the upcoming National Day holiday, there is a specific emphasis on focusing on dividend-paying sectors as a defensive strategy [2][10][14]

Market Overview - The market is expected to experience fluctuations next week, with liquidity shock indicators for the CSI 300 index at 1.86, indicating current market liquidity is 1.86 times higher than the average level over the past year [1] - The PUT-CALL ratio for the SSE 50 ETF options decreased to 0.91, reflecting a reduced caution among investors regarding the short-term performance of the SSE 50 ETF [1] - The average turnover rates for the SSE Composite Index and Wind All A Index were 1.27% and 1.91%, respectively, indicating a decline in trading activity [1] Macroeconomic Factors - The onshore and offshore RMB exchange rates experienced a weekly decline of -0.31% and -0.30%, respectively [1] - The US stock market showed a downward trend, with the Dow Jones, S&P 500, and Nasdaq indices recording weekly returns of -0.15%, -0.31%, and -0.65% [1] - Disagreements within the Federal Reserve regarding future monetary policy paths have increased, with some members advocating for rate cuts while others caution against it due to rising inflation [1] Industrial Performance - From January to August, China's industrial enterprises above designated size achieved a total profit of 46,929.7 billion yuan, reflecting a year-on-year growth of 0.9% [1] - In August, the profit of industrial enterprises turned from a decline of -1.5% in the previous month to a growth of 20.4% [1] Technical Analysis - The SAR indicator for the Wind All A Index showed an upward breakout on September 11 [1] - The current market score based on the moving average strength index is 150, positioned at the 53.3% percentile for 2023 [1] - The sentiment model score decreased to 1 point (out of 5), indicating a decline in market sentiment [1] Sector Analysis - The industry crowding degree is relatively high in sectors such as non-ferrous metals, communications, comprehensive, power equipment, and electronics, with notable increases in power equipment and media sectors [3]

- Liquidity shock indicator for CSI 300 index reached 1.86 on Friday, higher than the previous week's 1.33, indicating current market liquidity is 1.86 times the standard deviation above the past year's average level [7] - PUT-CALL ratio for SSE 50ETF options declined to 0.91 on Friday, lower than the previous week's 1.14, reflecting reduced investor caution regarding short-term movements of SSE 50ETF [7] - Five-day average turnover rates for SSE Composite Index and Wind All A Index were 1.27% and 1.91%, respectively, corresponding to the 75.73% and 81.47% percentiles since 2005, showing decreased trading activity [7] - SAR indicator for Wind All A Index showed a positive breakout on September 11 [10] - Moving average strength index for Wind All A Index scored 150, at the 53.3% percentile for 2023, indicating a fluctuating trend [10] - Sentiment model score was 1 out of 5, trend model signal was positive, and weighted model signal was negative [10] - Small-cap factor crowding score was 0.40, low-valuation factor crowding score was -0.67, high-profitability factor crowding score was -0.10, and high-growth factor crowding score was 0.15 [18] - Sub-scores for small-cap factor included valuation spread (1.08), pairwise correlation (0.06), market volatility (-0.42), and return reversal (0.85) [18] - Sub-scores for low-valuation factor included valuation spread (-1.25), pairwise correlation (-0.03), market volatility (-0.09), and return reversal (-1.32) [18] - Sub-scores for high-profitability factor included valuation spread (-0.17), pairwise correlation (0.14), market volatility (-0.84), and return reversal (0.48) [18] - Sub-scores for high-growth factor included valuation spread (1.91), pairwise correlation (0.46), market volatility (-0.94), and return reversal (-0.82) [18]

AI 赋能资产配置（十七） AI 盯盘： "9·24"行情案例 策略研究·策略解读 证券研究报告 | 2025年09月25日 | 证券分析师： | 王开 | 021-60933132 | wangkai8@guosen.com.cn | 执证编码：S0980521030001 | | --- | --- | --- | --- | --- | | 证券分析师： | 陈凯畅 | 021-60375429 | chenkaichang@guosen.com.cn | 执证编码：S0980523090002 | 事项： 金融市场中的短期内快速上涨行情往往因情绪驱动而非基本面改善，容易导致阶段性追高。传统技术分析 （如 KDJ、RSI、MACD、均线体系、成交量、换手率及估值水平等单一指标）虽能提供部分洞察，但其 信号纷杂、滞后性强且受主观经验影响较大，难以有效预警此类脉冲式行情的风险。 为系统性地解决这一问题，本研究旨在构建一个多维度、量化、由人工智能驱动的综合研判框架。研究首 先从趋势、动量、资金流向、估值四个核心维度出发，构建了十二个关键原始指标，形成一个全面刻画市 场状态的多因子体系，并初步判断和市场趋势的关 ...

Core Insights - The report emphasizes the need for a multi-dimensional, AI-driven framework to effectively predict and manage risks associated with short-term market surges, particularly in the context of the A-share market [2][3] - It introduces a comprehensive multi-factor system based on four core dimensions: trend, momentum, capital flow, and valuation, which collectively enhance market state characterization [2][4] - The AI-enhanced multi-factor timing strategy is expected to provide investors with an objective risk warning tool, reducing losses from blind chasing of high prices [3][4] Trend Analysis - The report illustrates that traditional indicators often fail to provide timely warnings for rapid market fluctuations driven by emotions rather than fundamentals [2][6] - The analysis of the "9·24" market surge shows that moving averages indicated a bullish trend before the surge, while subsequent signals indicated a weakening momentum [5][6][8] Momentum Indicators - The report highlights that extreme values in momentum indicators like KDJ and RSI often signal the end of a price surge, as seen during the "9·24" event where both indicators reached overbought levels [8][9] - The KDJ and RSI thresholds serve as critical points for identifying market cycles, aiding investors in timing their trades effectively [9] Capital Flow Insights - The report notes a strong correlation between trading volume and price movements during the "9·24" surge, indicating that volume often precedes price increases [11][12] - A decline in trading volume following price peaks serves as a warning signal for potential market corrections, as evidenced in the analysis [12] Valuation Metrics - The report discusses how valuation metrics, such as PE ratios, can indicate market risk accumulation, particularly when they exceed historical high thresholds [15][16] - The combination of high valuation levels and overbought momentum indicators has historically signaled market tops and subsequent corrections [15] AI-Driven Quantitative Strategy - The report outlines a comprehensive AI-driven quantitative strategy that automates the process of factor selection, modeling, and execution, enhancing the robustness of trading signals [19][20] - The strategy employs a closed-loop system that continuously optimizes itself based on real-time performance feedback, ensuring adaptability to changing market conditions [19][20] Factor Processing and Model Selection - The report emphasizes the importance of factor processing, including standardization and ranking, to ensure comparability and robustness of the indicators used in the model [30][33] - The HistGradientBoosting model is selected for its ability to capture non-linear relationships among factors, providing a more accurate timing signal for trades [39][40] Performance Evaluation - Backtesting results indicate that the AI-driven strategy significantly outperforms the market benchmark, achieving an annualized return of approximately 36.41% with a Sharpe ratio of 2.30 [41][42] - The strategy demonstrates strong risk management capabilities, maintaining a maximum drawdown of -19.51%, which is notably lower than the benchmark during volatile periods [45][46]