Group 1 - The core viewpoint of the article highlights the rapid switching of main lines in the stock market in 2025, with technology leading the charge, particularly in the AI industry and related sectors [2] - The fund manager, Jin Zicai, has effectively captured the explosive opportunities in the overseas computing power sector by strategically investing in sub-sectors like optical modules and PCBs, aligning with the surge in overseas computing power demand [2][28] - Jin Zicai's investment framework prioritizes "Beta first," allowing for dynamic adjustments in portfolio structure while maintaining a focus on core themes [2][4] Group 2 - Jin Zicai has a decade of experience in industry rotation and has developed a unique three-tier analysis system that evaluates macroeconomic cycles, industry trends, and individual stocks [4] - The performance of the fund "Caitong Value Momentum Mixed A" is highlighted, with a return of 833.15% since inception and a year-to-date return of 53.78% [5][6] - The fund's asset allocation strategy combines both strategic long-term assessments and tactical short-term adjustments based on market momentum [7] Group 3 - The article details specific stock purchases and their performance during Jin Zicai's management, including significant gains in stocks like Xinyisheng and Shijia Photon [9][14] - The fund has shown a pattern of buying stocks at low points and benefiting from subsequent price increases, demonstrating Jin Zicai's ability to time the market effectively [12][21] - The fund's performance is attributed to precise industry allocation and stock selection strategies, with a focus on sectors poised for growth, particularly in technology manufacturing [15][16] Group 4 - The article notes that the fund has made strategic adjustments in response to market conditions, such as increasing exposure to computing power and technology manufacturing while reducing holdings in other sectors [15][28] - Jin Zicai's approach includes a flexible strategy that allows for quick shifts in investment focus based on industry trends and economic conditions, which has been a key factor in achieving excess returns [14][28] - The overall sentiment is that the AI computing power sector is experiencing a significant boom, with expectations for continued growth in demand and investment in the coming quarters [28]

Quantitative Models and Construction Methods - **Model Name**: A-Share Multi-Dimensional Timing Model **Model Construction Idea**: The model evaluates the directional judgment of the A-share market using four dimensions: valuation, sentiment, capital, and technical indicators. Valuation and sentiment dimensions adopt a mean-reversion logic, while capital and technical dimensions use trend-following logic. The model combines these dimensions to provide a comprehensive view of market trends [2][9][15]. **Model Construction Process**: 1. The model uses the Wind All A Index as a proxy for the A-share market. 2. Each dimension generates daily signals with values of 0, ±1, representing neutral, bullish, or bearish views. 3. Valuation indicators include equity risk premium (ERP). 4. Sentiment indicators include option put-call ratio, implied volatility, and futures member position ratio. 5. Capital indicators include financing purchase amount. 6. Technical indicators include Bollinger Bands and the difference in the proportion of individual stock trading volume [11][15]. 7. The final multi-dimensional score is calculated as the sum of the scores from the four dimensions, determining the overall market view [9][15]. **Model Evaluation**: The model effectively captures market trends and provides actionable insights for timing decisions [9]. - **Model Name**: Style Timing Model **Model Construction Idea**: The model evaluates timing for dividend and size styles using trend-based indicators and crowding metrics [3][17][22]. **Model Construction Process**: 1. **Dividend Style Timing**: - The model uses three indicators: relative momentum of the CSI Dividend Index vs. CSI All Index, 10Y-1Y term spread, and interbank pledged repo transaction volume. - Each indicator generates daily signals with values of 0, ±1, representing neutral, bullish, or bearish views. - The final score is the sum of the three indicators, determining the overall view on dividend style [17][21]. 2. **Size Style Timing**: - The model uses the crowding degree of small-cap and large-cap styles, calculated based on momentum difference and trading volume ratio between the Wind Micro-Cap Index and CSI 300 Index. - Crowding degree is determined by averaging the top three results of six different window lengths for small-cap and large-cap styles. - High crowding is triggered when small-cap crowding exceeds 90% or large-cap crowding falls below 10%. - In high crowding zones, a small parameter double moving average model is used to capture short-term reversals. In low crowding zones, a large parameter double moving average model is used to follow medium- to long-term trends [22][24][26]. **Model Evaluation**: The model provides effective timing signals for style rotation, especially in different market conditions [22][24]. - **Model Name**: Industry Rotation Model **Model Construction Idea**: The model uses genetic programming to directly extract factors from industry index data, focusing on price-volume and valuation characteristics. It employs a dual-objective genetic programming approach to enhance factor diversity and reduce overfitting [4][29][32]. **Model Construction Process**: 1. The model uses 32 CITIC industry indices as underlying assets. 2. Factors are updated quarterly, and the model rebalances weekly. 3. The dual-objective genetic programming approach evaluates factors using |IC| and NDCG@5 metrics to assess monotonicity and performance of long positions. 4. Factors are combined using a greedy strategy and variance inflation factor to reduce collinearity. 5. The highest-weight factor is constructed as follows: - Perform cross-sectional regression of standardized monthly trading volume against the rolling 4-year percentile of price-to-book ratio (P/B). Take residuals as variable A. - Sum the smallest 9 values of variable A over the past 15 trading days to obtain variable B. - Standardize variable B using z-score, reverse values greater than 2.5, and sum the standardized values over the past 15 trading days [29][33][37]. **Model Evaluation**: The model effectively identifies industry rotation factors with strong monotonicity and performance, while reducing overfitting risks [29][33]. - **Model Name**: China Domestic All-Weather Enhanced Portfolio **Model Construction Idea**: The model adopts a macro factor risk parity framework, emphasizing risk diversification across underlying macro risk sources rather than asset classes. It actively allocates based on macro expectation momentum [5][38][41]. **Model Construction Process**: 1. **Macro Quadrant Division and Asset Selection**: Divide growth and inflation dimensions into four quadrants based on whether they exceed or fall short of expectations. Determine suitable assets for each quadrant using quantitative and qualitative methods. 2. **Quadrant Portfolio Construction and Risk Measurement**: Construct sub-portfolios with equal weights for assets within each quadrant, focusing on downside risk. 3. **Risk Budgeting Model for Quadrant Weights**: Adjust quadrant risk budgets monthly based on "quadrant views" derived from macro expectation momentum indicators, which consider buy-side expectation momentum and sell-side expectation deviation momentum [38][41]. **Model Evaluation**: The model effectively balances macro risks and enhances portfolio performance through active allocation [38][41]. --- Model Backtesting Results - **A-Share Multi-Dimensional Timing Model**: - Annualized Return: 25.23% - Maximum Drawdown: -28.46% - Sharpe Ratio: 1.17 - Calmar Ratio: 0.89 - Year-to-Date (YTD): 40.98% - Last Week's Return: 0.15% [14] - **Style Timing Model**: - **Dividend Style Timing**: - Annualized Return: 16.04% - Maximum Drawdown: -25.52% - Sharpe Ratio: 0.87 - Calmar Ratio: 0.63 - YTD: 21.75% - Last Week's Return: 0.23% [20] - **Size Style Timing**: - Annualized Return: 26.25% - Maximum Drawdown: -30.86% - Sharpe Ratio: 1.09 - Calmar Ratio: 0.85 - YTD: 65.89% - Last Week's Return: 1.07% [27] - **Industry Rotation Model**: - Annualized Return: 32.60% - Annualized Volatility: 17.95% - Sharpe Ratio: 1.82 - Maximum Drawdown: -19.63% - Calmar Ratio: 1.66 - Last Week's Return: 0.27% - YTD: 36.44% [32] - **China Domestic All-Weather Enhanced Portfolio**: - Annualized Return: 11.53% - Annualized Volatility: 6.16% - Sharpe Ratio: 1.87 - Maximum Drawdown: -6.30% - Calmar Ratio: 1.83 - Last Week's Return: 0.66% - YTD: 9.02% [42]

- The report introduces the **Diffusion Index Industry Rotation Model**, which tracks industry trends based on momentum strategies. The model has been monitored for four years, with notable performance in 2021 when it captured industry trends effectively, achieving an excess return of over 25% before experiencing a significant drawdown due to cyclical stock adjustments. In 2025, the model suggested allocating to industries such as comprehensive, non-ferrous metals, communication, banking, media, and retail trade[24][28] - The **Diffusion Index Industry Rotation Model** ranks industries weekly based on diffusion index values. As of September 26, 2025, the top six industries were communication (0.949), non-ferrous metals (0.927), banking (0.897), electronics (0.864), automotive (0.859), and comprehensive (0.811). The bottom six industries were food and beverage (0.153), non-bank finance (0.212), coal (0.342), construction (0.348), real estate (0.362), and consumer services (0.415)[25][26][27] - The **GRU Factor Industry Rotation Model** utilizes GRU deep learning networks to analyze minute-level price and volume data. It has shown strong adaptability in short cycles but performs less effectively in long cycles. The model has been operational since 2021, achieving significant excess returns initially. However, in 2025, the model faced challenges in capturing excess returns due to concentrated market themes and speculative trading[31][37] - The **GRU Factor Industry Rotation Model** ranks industries weekly based on GRU factor values. As of September 26, 2025, the top six industries were steel (3.15), real estate (2.6), building materials (2.08), petroleum and petrochemicals (1.85), transportation (0.81), and electric power and utilities (0.01). The bottom six industries were computing (-32.91), media (-29.46), communication (-17.57), food and beverage (-13.4), pharmaceuticals (-13.36), and non-ferrous metals (-12.73)[6][13][32] - The **Diffusion Index Industry Rotation Model** achieved an average weekly return of -0.00%, with an excess return of 0.78% compared to the equal-weighted return of CICC primary industries. Since September, the model has recorded an excess return of -1.10%, and a year-to-date excess return of 3.68%[23][28] - The **GRU Factor Industry Rotation Model** recorded an average weekly return of -0.61%, with an excess return of 0.17% compared to the equal-weighted return of CICC primary industries. Since September, the model has achieved an excess return of 0.07%, and a year-to-date excess return of -7.53%[31][34]

Group 1 - The article presents a series of reports focused on asset allocation strategies under various economic conditions, emphasizing the importance of macroeconomic factors in investment decisions [2][3] - It outlines multiple thematic reports, including those on industry rotation strategies, risk premium perspectives, and macroeconomic indicators, which are crucial for optimizing asset allocation [2][3] - The reports cover a wide range of topics, such as the impact of economic cycles on asset pricing, the effectiveness of Smart Beta strategies, and the analysis of historical patterns in interest rate cycles [2][3] Group 2 - The article highlights the significance of industry rotation strategies, detailing methods for selecting industries based on economic cycles, valuation reversals, and price momentum [3] - It discusses the application of quantitative models in industry configuration, focusing on factors like profitability and momentum as key determinants for successful industry selection [3] - The reports also explore the relationship between macroeconomic trends and industry performance, providing insights into how to capitalize on cyclical opportunities within various sectors [3]

1. Report Industry Investment Rating No information provided in the content. 2. Core View of the Report - On September 25, 2025, most convertible bond industries rose, and the valuation increased month - on - month. The CSI Convertible Bond Index rose 0.46% month - on - month, while the Shanghai Composite Index fell 0.01% month - on - month. The market style favored large - cap growth stocks. The trading sentiment in the convertible bond market weakened [1]. - The convertible bond price center increased, and the proportion of high - price bonds rose. The overall closing price weighted average of convertible bonds was 130.63 yuan, up 0.41% from the previous day. The valuation also increased, with the 100 - yuan parity fitted conversion premium rate rising 0.29 pct [2]. - In the A - share market, more than half of the underlying stock industry indices declined, with 23 industries falling. In the convertible bond market, 21 industries rose [3]. 3. Summary by Relevant Catalogs 3.1 Market Main Index Performance - The CSI Convertible Bond Index closed at 479.01, up 0.46% daily, down 0.09% in the past week, down 1.99% in the past month, and up 15.55% since the beginning of 2025. Other convertible bond - related indices and major A - share indices also showed different trends in daily, weekly, monthly, and year - to - date changes [6]. - In terms of style indices, large - cap growth stocks performed well, rising 1.28% daily, while large - cap value stocks fell 0.57% daily [7]. 3.2 Market Fund Performance - The trading volume of the convertible bond market was 7.7368 billion yuan, a 12.25% month - on - month decrease. The total trading volume of the Wind All - A Index was 239.1771 billion yuan, a 1.90% month - on - month increase. The net outflow of main funds from the Shanghai and Shenzhen stock markets was 23.6 billion yuan, and the yield of the 10 - year treasury bond decreased 1.82 bp to 1.88% [1]. 3.3 Convertible Bond Valuation - After excluding convertible bonds with a closing price > 150 yuan and a conversion premium rate > 50%, the 100 - yuan parity fitted conversion premium rate was 28.71%, up 0.29 pct, at the 96.90% quantile since 2019. The overall weighted average parity was 100.56, down 0.14%. The price median was 130.2, down 0.01%, at the 98.10% quantile since 2019 [15][19]. - The conversion premium rates of convertible bonds classified by stock - bond nature all increased, with the conversion premium rate of equity - biased convertible bonds rising 1.15 pct [27]. 3.4 Industry Rotation - In the A - share market, the top three industries with the largest declines were Textile and Apparel (- 1.45%), Agriculture, Forestry, Animal Husbandry and Fishery (- 1.22%), and Household Appliances (- 1.07%). The top three industries with the largest increases were Media (+ 2.23%), Communication (+ 1.99%), and Non - Ferrous Metals (+ 1.87%). - In the convertible bond market, the top three industries with the largest increases were Environmental Protection (+ 2.46%), Non - Ferrous Metals (+ 1.62%), and Automobile (+ 1.22%). The top three industries with the largest declines were Building Decoration (- 0.49%), Basic Chemicals (- 0.21%), and Light Industry Manufacturing (- 0.19%) [3][55].

Market Performance Overview - The domestic equity market indices showed mixed performance during the week of September 15-19, 2025, with the ChiNext Index rising by 2.34% [4] - In terms of sectors, coal, power equipment, and electronics industries had the highest gains, while banking, non-ferrous metals, and non-bank financial sectors experienced the largest declines [4] Fund Product Issuance - The domestic new fund market saw increased activity, with 63 new funds established, totaling 748.28 billion units issued. This included 27 bond funds, 27 equity funds, 7 mixed funds, 1 international (QDII) fund, and 1 REIT [5] - A total of 31 new funds were issued across the market, with 21 being equity funds, 4 FOF funds, 4 mixed funds, 1 bond fund, and 1 international (QDII) fund [5] Fund Product Performance Tracking - Various industry-themed funds exhibited volatile and divergent performance, with TMT theme funds continuing to show a net value increase of 2.56%, while financial and real estate theme funds saw a notable decline [6] - As of September 19, 2025, the performance of different themed funds was as follows: New Energy (2.07%), National Defense and Military Industry (1.50%), Balanced Industry (0.92%), Rotation Industry (0.49%), Consumption (-0.53%), Cyclical (-1.63%), Pharmaceutical (-2.41%), and Financial Real Estate (-2.68%) [6] ETF Market Tracking - Domestic stock ETFs experienced a net inflow of funds, while Hong Kong stock ETFs maintained significant inflows. Specifically, stock ETFs had a median return of 0.03% with a net inflow of 77.93 billion yuan [7] - Hong Kong stock ETFs recorded a median return of 0.84% with a net inflow of 166.52 billion yuan, and cross-border ETFs had a median return of 1.56% with a net inflow of 1.227 billion yuan [8] Fund Positioning Monitoring - The estimated equity positioning of actively managed funds decreased by 0.27 percentage points compared to the previous week. Increased allocations were observed in the automotive, electronics, and basic chemicals sectors, while banking, pharmaceutical, and agriculture sectors saw reduced allocations [9] ESG Financial Products Tracking - A total of 34 new green bonds were issued this week, with a cumulative issuance scale of 379.48 billion yuan. The domestic green bond market has steadily developed, with a total issuance scale of 4.82 trillion yuan and 4,153 bonds issued as of September 19, 2025 [10] - The median net value changes for ESG funds were as follows: active equity funds (1.42%), passive equity index funds (0.21%), and bond ESG funds (0.04%). Funds focused on climate change, low-carbon economy, and carbon neutrality showed significant performance advantages [10]

Core Viewpoint - The GuoXin Quantitative Team has made significant research contributions over the past year, focusing on various investment strategies and market trends, showcasing their effectiveness and potential for investment opportunities [1]. Team Overview - The GuoXin Quantitative Team consists of 7 members specializing in areas such as active quantitative stock selection, index enhancement, factor research, FOF investment, fund research, industry rotation, asset allocation, Hong Kong stock investment, and CTA strategies [1]. Research Highlights - The team has produced a selection of research reports that cover a wide range of investment strategies, including: - Active quantitative stock selection strategies - Factor-based stock selection and index enhancement strategies - Market trend analysis and research on hot sectors - FOF and fund research series [1][8][10]. Performance Metrics - The "Super Expectation Selected Portfolio" has achieved an annualized return of 36.04% since 2010, outperforming the CSI 500 Index by 32.90% [11][12]. - The "Growth Steady Portfolio" has maintained an annualized return of 41.15% since 2012, exceeding the CSI 500 Index by 34.84% [14][16]. - The "Brokerage Golden Stock Performance Enhancement Portfolio" has delivered an annualized return of 21.78%, consistently ranking in the top 30% of active equity funds since 2018 [19][21]. Strategy Insights - The "Small Cap Selected Portfolio" has generated an annualized return of 39.22% since 2014, outperforming the CSI 2000 Index by 28.66% [25][27]. - The "Stable Selected Portfolio" has achieved an annualized return of 26.18% since 2012, with a lower maximum drawdown compared to the CSI Dividend Total Return Index [30][32]. - The "Multi-Strategy Enhanced Portfolio" has recorded an annualized return of 23.43% since 2013, with a significant information ratio of 2.60 [34]. Sector Rotation Strategies - The "Key Moment Leading Sheep Strategy" has identified strong momentum effects in the A-share market, achieving an annualized return of 25.29% since 2013, outperforming the CSI All Index by 19.65% [39][40].

Group 1 - The core viewpoint indicates that the A-share market shows a low probability of rising in the five trading days before the National Day holiday, but the last trading day before the holiday has a 70% probability of an increase, while the market tends to rise after the holiday [1][6] - Historical data from 2015 to 2024 shows that the Shanghai Composite Index has a 70% probability of rising on the first trading day after the holiday and a 60% probability of rising in the following five trading days [2][6] - The leading sectors in the A-share market before and after the National Day holiday exhibit significant rotation, covering various fields such as consumption, pharmaceuticals, and technology [6][7] Group 2 - The leading sectors for the five trading days before the holiday from 2020 to 2024 include Food & Beverage, Social Services, and Defense & Military, while the sectors leading after the holiday include Electronics, Automotive, and Pharmaceuticals [4][6] - The market is expected to maintain a volatile pattern before the holiday, influenced by factors such as the Federal Reserve's interest rate decisions and potential profit-taking by investors [6][7] - The financing trend typically shows a pattern of "contraction before the holiday and explosion after," indicating a shift in risk appetite post-holiday [7]

Quantitative Models and Construction Methods 1. Model Name: Convertible Bond Random Forest Strategy - **Model Construction Idea**: Utilizes the Random Forest machine learning method to identify convertible bonds with potential for excess returns by leveraging decision trees[16][17] - **Model Construction Process**: 1. Data preprocessing and feature engineering to prepare convertible bond datasets 2. Training a Random Forest model with historical data to identify patterns of excess return potential 3. Selecting bonds with the highest predicted scores for portfolio construction 4. Weekly rebalancing of the portfolio based on updated predictions[17] - **Model Evaluation**: Demonstrated strong performance in generating excess returns, indicating high predictive accuracy[16] 2. Model Name: Multi-Dimensional Timing Model - **Model Construction Idea**: Combines macro, meso, micro, and derivative signals to create a four-dimensional non-linear timing model for market positioning[18][19] - **Model Construction Process**: 1. Macro signals: Derived from liquidity, interest rates, credit, economic growth, and exchange rates 2. Meso signals: Based on industry-level business cycle indicators 3. Micro signals: Captures structural risks using valuation, risk premium, volatility, and liquidity factors 4. Derivative signals: Generated from the basis of stock index futures 5. Aggregation: Signals are synthesized into a composite timing signal[18][19][24] - **Model Evaluation**: Effective in identifying market trends and providing actionable signals, with the latest signal indicating a bullish stance[19][24] 3. Model Name: Industry Rotation Strategy 2.0 - **Model Construction Idea**: Constructs an industry rotation strategy based on economic quadrants and multi-dimensional industry style factors[69] - **Model Construction Process**: 1. Define economic quadrants using corporate earnings and credit conditions 2. Develop industry style factors such as expected business climate, earnings surprises, momentum, valuation bubbles, and inflation beta 3. Test factor effectiveness within each quadrant 4. Allocate to high-expected-return industries based on factor signals[69][71] - **Model Evaluation**: Demonstrates strong adaptability to the A-share market, with annualized excess returns of 9.44% (non-exclusion version) and 10.14% (double-exclusion version)[71] 4. Model Name: Genetic Programming Index Enhancement Models - **Model Construction Idea**: Uses genetic programming to discover and optimize stock selection factors for index enhancement strategies[88][93][97] - **Model Construction Process**: 1. Stock pools: Defined for CSI 300, CSI 500, CSI 1000, and CSI All Share indices 2. Training: Genetic programming generates initial factor populations and iteratively evolves them through multiple generations 3. Factor selection: Top-performing factors are combined into a composite score 4. Portfolio construction: Selects top 10% of stocks within each industry based on scores, with weekly rebalancing[88][93][97][102] - **Model Evaluation**: - CSI 300: Annualized excess return of 17.91%, Sharpe ratio of 1.05[91] - CSI 500: Annualized excess return of 11.78%, Sharpe ratio of 0.85[95] - CSI 1000: Annualized excess return of 17.97%, Sharpe ratio of 0.93[98] - CSI All Share: Annualized excess return of 24.84%, Sharpe ratio of 1.33[103] --- Model Backtest Results 1. Convertible Bond Random Forest Strategy - Weekly excess return: 0.64%[16] 2. Multi-Dimensional Timing Model - Latest composite signal: Bullish (1)[19][24] 3. Industry Rotation Strategy 2.0 - Annualized excess return (non-exclusion version): 9.44% - Annualized excess return (double-exclusion version): 10.14%[71] 4. Genetic Programming Index Enhancement Models - CSI 300: - Annualized excess return: 17.91% - Sharpe ratio: 1.05[91] - CSI 500: - Annualized excess return: 11.78% - Sharpe ratio: 0.85[95] - CSI 1000: - Annualized excess return: 17.97% - Sharpe ratio: 0.93[98] - CSI All Share: - Annualized excess return: 24.84% - Sharpe ratio: 1.33[103] --- Quantitative Factors and Construction Methods 1. Factor Name: Industry Business Climate Index 2.0 - **Factor Construction Idea**: Tracks industry fundamentals by analyzing revenue, pricing, and cost dynamics[27] - **Factor Construction Process**: 1. Analyze industry revenue and cost structures 2. Calculate daily market-cap-weighted industry indices 3. Aggregate indices into a composite business climate index[27][30] - **Factor Evaluation**: Demonstrates predictive power for A-share earnings expansion cycles[28] 2. Factor Name: Barra CNE6 Style Factors - **Factor Construction Idea**: Evaluates market performance using 9 primary and 20 secondary style factors, including size, volatility, momentum, quality, value, and growth[45] - **Factor Construction Process**: 1. Calculate factor returns for each style factor 2. Aggregate factor performance to assess market trends[45][46] - **Factor Evaluation**: Size factor performed well during the week, while volatility factor underperformed[46] 3. Factor Name: Industry Rotation Factors - **Factor Construction Idea**: Captures industry rotation dynamics using factors like expected business climate, earnings surprises, momentum, and valuation bubbles[69] - **Factor Construction Process**: 1. Define and calculate individual factors 2. Test factor effectiveness within economic quadrants 3. Combine factors for industry allocation[69] - **Factor Evaluation**: Demonstrates strong historical performance, with factors like expected business climate and momentum showing significant returns[57][59] --- Factor Backtest Results 1. Industry Business Climate Index 2.0 - Current value: 0.913 - Excluding financials: 1.288[28] 2. Barra CNE6 Style Factors - Size factor: Strong performance during the week[46] 3. Industry Rotation Factors - Historical annualized returns: - Expected business climate: 0.40% - Momentum: -0.95% - Valuation beta: 2.37%[57]

Quantitative Models and Construction Methods 1. Model Name: Diffusion Index Industry Rotation Model - **Model Construction Idea**: The model is based on the principle of price momentum, aiming to capture upward trends in industries through a diffusion index[26][27] - **Model Construction Process**: 1. Calculate the diffusion index for each industry based on price momentum 2. Rank industries by their diffusion index values 3. Select top industries for allocation based on their rankings 4. Adjust the portfolio monthly or weekly based on updated diffusion index rankings[26][27] - **Model Evaluation**: The model has shown stable performance in certain years (e.g., 2022 with an annual excess return of 6.12%) but struggled during market reversals or concentrated market themes, such as in 2024 and 2025[26][33] 2. Model Name: GRU Factor Industry Rotation Model - **Model Construction Idea**: This model leverages GRU (Gated Recurrent Unit) deep learning networks to process high-frequency volume and price data, aiming to identify industry rotation opportunities[38] - **Model Construction Process**: 1. Input high-frequency volume and price data into the GRU network 2. Train the GRU model on historical data to identify patterns in industry rotation 3. Generate factor scores for industries based on the GRU model's output 4. Rank industries by their GRU factor scores and allocate to top-ranked industries[38][34] - **Model Evaluation**: The model performs well in short cycles but struggles in long cycles or extreme market conditions. It has shown difficulty in capturing excess returns in concentrated market themes during 2025[33][38] --- Model Backtesting Results 1. Diffusion Index Industry Rotation Model - **Weekly Average Return**: -1.74%[30] - **Excess Return (Weekly)**: -1.41%[30] - **Excess Return (September 2025)**: -1.88%[30] - **Excess Return (2025 YTD)**: 2.76%[25][30] 2. GRU Factor Industry Rotation Model - **Weekly Average Return**: -0.72%[36] - **Excess Return (Weekly)**: -0.38%[36] - **Excess Return (September 2025)**: -0.10%[36] - **Excess Return (2025 YTD)**: -7.78%[33][36] --- Quantitative Factors and Construction Methods 1. Factor Name: Diffusion Index - **Factor Construction Idea**: Measures the breadth of price momentum across industries to identify upward trends[26][27] - **Factor Construction Process**: 1. Calculate the proportion of stocks in an industry with positive price momentum 2. Aggregate these proportions to derive the diffusion index for the industry 3. Rank industries based on their diffusion index values[27][28] - **Factor Evaluation**: Effective in capturing upward trends but vulnerable to reversals and underperformance in counter-trend markets[26][33] 2. Factor Name: GRU Factor - **Factor Construction Idea**: Utilizes GRU deep learning to analyze high-frequency trading data and generate predictive scores for industry rotation[38] - **Factor Construction Process**: 1. Input high-frequency trading data into the GRU network 2. Train the model to recognize patterns in industry rotation 3. Output factor scores for industries based on the model's predictions[38][34] - **Factor Evaluation**: Strong in short-term predictions but less effective in long-term or extreme market conditions[33][38] --- Factor Backtesting Results 1. Diffusion Index - **Top Industries (Weekly)**: Non-ferrous Metals (0.978), Banking (0.968), Communication (0.946), Electronics (0.877), Automotive (0.874), Retail (0.873)[27] - **Bottom Industries (Weekly)**: Food & Beverage (0.354), Real Estate (0.46), Coal (0.487), Transportation (0.543), Construction (0.574), Building Materials (0.618)[27] 2. GRU Factor - **Top Industries (Weekly)**: Non-ferrous Metals (7.4), Petrochemicals (5.38), Coal (4.17), Steel (4.15), Building Materials (3.46), Non-banking Financials (3.08)[34] - **Bottom Industries (Weekly)**: Comprehensive Finance (-19.42), Utilities (-13.41), Electronics (-13.18), Pharmaceuticals (-11.14), Automotive (-10.07), Consumer Services (-10.04)[34]