- The report includes multiple quantitative models for market timing, categorized into short-term, medium-term, and long-term models. Short-term models include the "Volume Model" (neutral for all broad-based indices), "Feature Institutional Model" (bullish), "Feature Volume Model" (bearish), and "Smart Algorithm Models" (bearish for CSI 300 and CSI 500 indices) [1][11][62][63]. Medium-term models include the "Limit-Up and Limit-Down Model" (neutral), "Up-Down Return Difference Model" (bullish), and "Calendar Effect Model" (neutral) [12][64]. Long-term models include the "Long-Term Momentum Model" (bullish) [13][65]. Comprehensive models such as "A-Share Comprehensive Weapon V3 Model" and "A-Share Comprehensive CSI 2000 Model" are bearish [14][65]. - The "Volume Model" is constructed based on trading volume data, aiming to capture short-term market sentiment [1][11]. The "Feature Institutional Model" leverages institutional trading patterns observed in the market [1][11]. The "Feature Volume Model" focuses on specific volume characteristics to predict market trends [1][11]. The "Smart Algorithm Models" utilize machine learning algorithms to analyze historical data and predict market movements [1][11][62][63]. The "Limit-Up and Limit-Down Model" analyzes the frequency and impact of limit-up and limit-down events [12][64]. The "Up-Down Return Difference Model" calculates the difference between upward and downward returns to assess market direction [12][64]. The "Calendar Effect Model" incorporates seasonal and calendar-based effects on market performance [12][64]. The "Long-Term Momentum Model" evaluates long-term price trends to predict future movements [13][65]. Comprehensive models combine signals from multiple individual models to provide an overall market outlook [14][65]. - Evaluation of these models indicates that short-term models show mixed signals, with some bullish and others bearish, reflecting market uncertainty [1][11][62][63]. Medium-term models are generally neutral to bullish, suggesting moderate optimism [12][64]. Long-term models are bullish, indicating strong confidence in sustained upward trends [13][65]. Comprehensive models are bearish, signaling caution in the overall market outlook [14][65]. - Backtesting results for the models are not explicitly detailed in the report, but the report mentions the performance of specific indices and their alignment with model predictions. For example, the CSI 300 index showed bearish signals from the "Smart Algorithm Model," aligning with its weekly decline of 1.08% [8][11][63]. Similarly, the "Up-Down Return Difference Model" showed bullish signals, consistent with positive medium-term outlooks [12][64]. - The report also includes quantitative factor-based strategies such as "Double-Bottom Pattern" and "Cup-and-Handle Pattern." The "Double-Bottom Pattern" achieved a weekly return of 4.09%, outperforming the Shanghai Composite Index by 4.61% [40][47]. The "Cup-and-Handle Pattern" achieved a weekly return of 0.6%, outperforming the Shanghai Composite Index by 1.12% [40][41]. These factors are constructed based on technical chart patterns and are evaluated for their relative performance against benchmark indices [40][41][47].

金融工程 证 券 研 究 报 告 【金工周报】（20250922-20250926） 部分指数依旧看多，后市或先抑后扬 ❖ 本周回顾 本周市场普遍上涨，上证指数单周上涨 0.21%，创业板指单周上涨 1.96%。 A 股模型： 短期：成交量模型所有宽基指数中性。低波动率模型中性。特征龙虎榜机构模 型看多。特征成交量模型看空。智能算法沪深 300 模型看空，智能算法中证 500 模型看空。 中期：涨跌停模型中性。月历效应模型中性。 长期：长期动量模型看多。 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多。 本周行业指数涨少跌多，涨幅前五的行业为：电子、有色金属、电力设备及新 能源、电力及公用事业、传媒，跌幅前五的行业为：消费者服务、商贸零售、 轻工制造、纺织服装、食品饮料。从资金流向角度来说，所有行业主力资金净 流出，其中电子、计算机、机械、医药、通信主力资金净流出居前。 本周股票型基金总仓位为 93.70%，相较于上周增加了 31 个 bps，混合型基金 总仓位 92.73%，相较于上周减少了 36 个 bps。 本周股票型 ETF 平均收益 ...

- The report includes multiple quantitative models for A-share market timing, such as "Volume Model," "Low Volatility Model," "Feature Institutional Model," "Feature Volume Model," "Smart CSI 300 Model," "Smart CSI 500 Model," "Limit-Up/Down Model," "Calendar Effect Model," "Long-Term Momentum Model," "Comprehensive Weapon V3 Model," and "Comprehensive CSI 2000 Model"[1][10][11][12][13] - The report also includes a Hong Kong market timing model, specifically the "Turnover Inverse Volatility Model"[14][73] - The construction of these models is based on principles such as price-volume relationships, acceleration and trend analysis, momentum, limit-up/down patterns, and calendar effects. The models are designed to cover short-term, medium-term, and long-term cycles, forming a multi-strategy system[8][10][11] - The report evaluates the models qualitatively, stating that timing strategies should be simple and universal, emphasizing the importance of coupling signals from different models or cycles to achieve a balance between offensive and defensive strategies[8][10][11] - The latest signals from the models indicate mixed results: some models are bullish (e.g., Volume Model, Feature Volume Model, Limit-Up/Down Model, Comprehensive Weapon V3 Model, Comprehensive CSI 2000 Model), while others are neutral or bearish (e.g., Low Volatility Model, Feature Institutional Model, Smart CSI 300 Model, Smart CSI 500 Model)[10][11][12][13] - Backtesting results for specific models or factors are not explicitly detailed in the report, but the report mentions that the "Comprehensive Weapon V3 Model" and "Comprehensive CSI 2000 Model" are bullish overall[13][72] - The Hong Kong market model, "Turnover Inverse Volatility Model," continues to show bullish signals for the Hang Seng Index[14][73]

Quantitative Models and Construction 1. Model Name: Volume Model - **Model Construction Idea**: This model evaluates market timing based on trading volume dynamics[10][64] - **Model Evaluation**: The model currently signals a neutral stance for the short term[10][64] 2. Model Name: Low Volatility Model - **Model Construction Idea**: This model assesses market timing by analyzing low volatility trends in the market[10][64] - **Model Evaluation**: The model currently signals a neutral stance for the short term[10][64] 3. Model Name: Institutional Feature Model (Dragon-Tiger List) - **Model Construction Idea**: This model uses institutional trading features from the Dragon-Tiger list to predict market movements[10][64] - **Model Evaluation**: The model currently signals a bearish outlook for the short term[10][64] 4. Model Name: Feature Volume Model - **Model Construction Idea**: This model leverages specific volume features to predict market trends[10][64] - **Model Evaluation**: The model currently signals a bearish outlook for the short term[10][64] 5. Model Name: Intelligent CSI 300 Model - **Model Construction Idea**: This model applies intelligent algorithms to predict movements in the CSI 300 index[10][64] - **Model Evaluation**: The model currently signals a bullish outlook for the short term[10][64] 6. Model Name: Intelligent CSI 500 Model - **Model Construction Idea**: This model applies intelligent algorithms to predict movements in the CSI 500 index[10][64] - **Model Evaluation**: The model currently signals a bearish outlook for the short term[10][64] 7. Model Name: Limit-Up/Down Model - **Model Construction Idea**: This model evaluates market timing based on the frequency of limit-up and limit-down events[11][65] - **Model Evaluation**: The model currently signals a bullish outlook for the mid-term[11][65] 8. Model Name: Calendar Effect Model - **Model Construction Idea**: This model incorporates calendar-based patterns to predict market movements[11][65] - **Model Evaluation**: The model currently signals a neutral stance for the mid-term[11][65] 9. Model Name: Long-Term Momentum Model - **Model Construction Idea**: This model evaluates long-term market trends using momentum indicators[12][66] - **Model Evaluation**: The model currently signals a neutral stance across all broad-based indices for the long term[12][66] 10. Model Name: A-Share Comprehensive Weapon V3 Model - **Model Construction Idea**: This model integrates multiple signals to provide a comprehensive market timing prediction[13][67] - **Model Evaluation**: The model currently signals a bearish outlook for the A-share market[13][67] 11. Model Name: A-Share Comprehensive CSI 2000 Model - **Model Construction Idea**: This model focuses on the CSI 2000 index, combining various timing signals[13][67] - **Model Evaluation**: The model currently signals a neutral stance for the A-share market[13][67] 12. Model Name: Turnover-to-Volatility Model (Hong Kong Market) - **Model Construction Idea**: This model evaluates market timing in the Hong Kong market by analyzing turnover relative to volatility[14][68] - **Model Evaluation**: The model currently signals a bullish outlook for the mid-term[14][68] --- Model Backtesting Results 1. Volume Model - **Short-Term Signal**: Neutral[10][64] 2. Low Volatility Model - **Short-Term Signal**: Neutral[10][64] 3. Institutional Feature Model (Dragon-Tiger List) - **Short-Term Signal**: Bearish[10][64] 4. Feature Volume Model - **Short-Term Signal**: Bearish[10][64] 5. Intelligent CSI 300 Model - **Short-Term Signal**: Bullish[10][64] 6. Intelligent CSI 500 Model - **Short-Term Signal**: Bearish[10][64] 7. Limit-Up/Down Model - **Mid-Term Signal**: Bullish[11][65] 8. Calendar Effect Model - **Mid-Term Signal**: Neutral[11][65] 9. Long-Term Momentum Model - **Long-Term Signal**: Neutral across all broad-based indices[12][66] 10. A-Share Comprehensive Weapon V3 Model - **Comprehensive Signal**: Bearish[13][67] 11. A-Share Comprehensive CSI 2000 Model - **Comprehensive Signal**: Neutral[13][67] 12. Turnover-to-Volatility Model (Hong Kong Market) - **Mid-Term Signal**: Bullish[14][68]