Core Viewpoint - The recent public fund quarterly reports indicate a significant increase in the electronic industry's allocation, reaching over 25%, marking the highest single-industry allocation in the past fifteen years [2][3]. Group 1: Industry Allocation Insights - The electronic industry's allocation surpassing 25% is notable, as it reflects a trend where public funds have historically struggled to maintain allocations above 20% without subsequent market adjustments [2][5]. - Historical data shows that when public fund allocations to a single industry exceed 20%, it often leads to subsequent pressure on absolute returns, with most instances since 2010 resulting in declines in relative performance [2][5]. - The report from Huatai Securities suggests that the average duration of core asset accumulation is around ten quarters, with current electronic sector allocations slightly above this average [3]. Group 2: Market Behavior and Predictions - The analysis indicates that during periods of improved market risk, sectors with increased allocations have an 86% probability of generating excess returns in the following quarter [3]. - Historical patterns reveal that high allocations often coincide with market changes, and the peak in holdings may be driven more by industry price increases rather than active accumulation [5]. - The electronic sector's current allocation has surpassed previous historical limits, yet it is essential to monitor the underlying fundamentals for potential acceleration in growth [5]. Group 3: Contextual Analysis - The report highlights that while the current allocation in the electronic sector is high, it does not necessarily indicate an immediate need for rebalancing, as the sector may continue to perform well if the fundamentals support it [5][6]. - The analysis serves as a window into market sentiment, providing insights into which sectors are currently attracting more attention from investors [6].

- The report constructs a market style rotation solution based on macro data, including value-growth style rotation strategy and large-small cap style rotation strategy. The value-growth style rotation strategy scores higher for growth style with a comprehensive score of 6 as of October 31, 2025[6][8] - The large-small cap style rotation strategy scores higher for small cap style with a comprehensive score of 4 as of October 31, 2025[8][10] - The industry rotation solution is constructed using four dimensions: macro indicators, fundamental indicators, technical indicators, and crowding indicators, forming a comprehensive evaluation system for industry rotation[11][22] - The macro indicators divide the primary industries into five sectors: upstream cycle, midstream manufacturing, downstream consumption, TMT, and big finance, based on the second-order difference of macro growth and liquidity[13] - The fundamental indicators include historical prosperity, prosperity changes, and prosperity expectations. As of October 31, 2025, the top five industries ranked by fundamental indicators are non-bank finance, non-ferrous metals, electronics, communication, and power equipment and new energy[17] - The technical indicators include index momentum, leading stock momentum, and K-line patterns. As of October 31, 2025, the top five industries ranked by technical indicators are communication, media, banking, computer, and machinery[18] - The crowding indicators include financing inflow, turnover rate, and transaction ratio. As of October 31, 2025, the top five industries ranked by crowding indicators are power equipment and new energy, non-ferrous metals, coal, electronics, and communication[21] - The comprehensive industry rotation score, combining the four dimensions, ranks the top seven industries as banking, machinery, communication, non-ferrous metals, media, automotive, and electronics as of October 31, 2025[22][25] Model Backtest Results - Value-Growth Style Rotation Strategy: Comprehensive score of 6, growth style scored higher[6][8] - Large-Small Cap Style Rotation Strategy: Comprehensive score of 4, small cap style scored higher[8][10] Factor Backtest Results - Fundamental Indicators: Top five industries are non-bank finance, non-ferrous metals, electronics, communication, and power equipment and new energy[17] - Technical Indicators: Top five industries are communication, media, banking, computer, and machinery[18] - Crowding Indicators: Top five industries are power equipment and new energy, non-ferrous metals, coal, electronics, and communication[21] - Comprehensive Industry Rotation Score: Top seven industries are banking, machinery, communication, non-ferrous metals, media, automotive, and electronics[22][25]

Core Insights - The report highlights a significant improvement in both revenue and profit growth for the A-share market in Q3 2025, with a notable turnaround in net profit growth for non-financial sectors [3][4] - The overall revenue growth for the A-share market reached 3.7% year-on-year in Q3 2025, compared to -0.2% in Q1 and 0.4% in Q2, while non-financial sectors saw a revenue growth of 2.3% [3][4] - Net profit growth for the entire A-share market was 11.4% year-on-year in Q3 2025, a significant increase from 3.8% in Q1 and 1.4% in Q2, with non-financial sectors showing a profit growth of 3.9% [3][4] Structural Perspective - The report indicates that the performance of major broad-based indices has improved across the board, with the ChiNext and STAR Market showing the highest earnings elasticity [4][10] - In Q3 2025, the ChiNext and STAR Market reported net profit growth rates of 58.3% and 32.8% respectively, with significant quarter-on-quarter improvements [4][10] - The dual drivers of high-tech prosperity and cyclical recovery are emphasized, with sectors like media, electronics, power equipment, and defense showing substantial profit growth exceeding 30% year-on-year [4][10] Stock Price Performance - The report notes that stock prices in the real estate and construction sectors have been more active following the mid-year earnings disclosures, indicating a market expectation for sector rotation [5] - The sectors with the most notable mid-year earnings growth are concentrated in technology manufacturing and certain cyclical industries like steel and non-ferrous metals [5] - The report suggests that the market's expectation for sector rotation is strengthening, particularly in sectors with high policy expectations, such as real estate and cyclical products [5]

- The report tracks various market environment factors, including stock market factors, commodity market factors, options market factors, and convertible bond market factors [1][7][11] - **Stock Market Factors**: - **Market Style**: The style of large-cap and small-cap stocks was balanced, while the value-growth style leaned towards growth [11][13] - **Market Style Volatility**: Both large-cap/small-cap and value-growth style volatilities increased [11][13] - **Market Structure**: Industry excess return dispersion increased, industry rotation speed decreased, and the proportion of rising constituent stocks increased [11][13] - **Trading Concentration**: The transaction amount of the top 100 stocks slightly decreased, while the transaction amount of the top 5 industries remained unchanged compared to the previous period [11][13] - **Market Activity**: Market volatility increased, and market turnover rate decreased [12][13] - **Commodity Market Factors**: - **Trend Strength**: Precious metals and agricultural products showed a decline in trend strength, while other sectors experienced an increase [26][32] - **Basis Momentum**: Basis momentum increased across all sectors [26][32] - **Volatility**: Volatility rose in all sectors except for the black sector [26][32] - **Liquidity**: Liquidity decreased in precious metals, non-ferrous metals, and agricultural products [26][32] - **Options Market Factors**: - **Implied Volatility**: Implied volatility for the SSE 50 and CSI 1000 indices decreased, reflecting a moderation in market expectations regarding Trump's tariff policies [35] - **Implied Discount Rate**: The implied discount rate for CSI 1000 narrowed, but the market did not turn fully optimistic [35] - **Option Holdings**: Both put and call option holdings increased, indicating persistent market uncertainty [35] - **Convertible Bond Market Factors**: - **Market Recovery**: The convertible bond market showed slight recovery last week [37] - **Valuation**: Pure bond premium rates remained stable, while the premium rate for 100-yuan convertible bonds steadily increased [37] - **Low Premium Convertible Bonds**: The proportion of low premium convertible bonds decreased significantly [37] - **Market Turnover**: Market transaction volume stabilized without further contraction [37]

Quantitative Models and Construction Methods 1. Model Name: Stock Timing Model - **Construction Idea**: The model is based on the comprehensive judgment of economic growth and liquidity easing[18] - **Construction Process**: - Construct timing factors from two core dimensions: economic growth and liquidity easing[18] - Factors include PMI YoY smoothed value, manufacturing fixed asset investment completion amount cumulative YoY, CPI YoY smoothed value, and new medium and long-term loans cumulative value YoY[19] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if indicator improves} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using CSI 800 total return as the benchmark[19] - **Evaluation**: The model effectively captures stock market cycles, avoiding downturns[21] 2. Model Name: Bond Timing Model - **Construction Idea**: The model analyzes from the perspective of monetary liquidity supply and demand[23] - **Construction Process**: - Factors include DR007, SHIBOR, and social financing scale stock YoY smoothed value[24] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if short-term average < long-term average} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using ChinaBond Treasury Total Net Price Index as the benchmark[24] - **Evaluation**: The model captures bond market trends, minimizing drawdowns[25] 3. Model Name: All-Weather Strategy - **Construction Idea**: The model adjusts risk budgets for different assets based on timing signals[17] - **Construction Process**: - Use a risk parity model to allocate risk contributions of assets[30] - Adjust risk budgets based on stock and bond timing signals[32] - Optimize the model: $$ \begin{array}{c} \min \sum_{i=1}^{N} \left( RC_i - b_i \sigma_p \right)^2 \\ \text{s.t.} \sum_{i=1}^{N} \omega_i = 1 \\ 0 \leq \omega_i \leq 1 \end{array} $$ - Backtest using a combination of CSI 800, ChinaBond Treasury Total Wealth Index, CSI Convertible Bond Index, S&P 500 ETF, and AAA Credit Bonds[31] - **Evaluation**: The strategy provides higher absolute returns while controlling risk[38] Model Backtest Results Stock Timing Model - Annualized Return: 14.1%[21] - Benchmark Annualized Return: 5.4%[21] - Excess Annualized Return: 8.7%[21] - Monthly Win Rate: 56.7%[21] Bond Timing Model - Annualized Return: 2.3%[25] - Benchmark Annualized Return: 1.1%[25] - Excess Annualized Return: 1.1%[25] - Monthly Win Rate: 68.3%[25] All-Weather Strategy - Annualized Return: 6.1%[38] - Benchmark Annualized Return: 5.1%[38] - Excess Annualized Return: 1.0%[38] - Maximum Drawdown: 2.6%[38] - Sharpe Ratio: 2.04[38] Quantitative Factors and Construction Methods 1. Factor Name: Value-Growth Rotation Factor - **Construction Idea**: The factor is based on economic recovery, liquidity, and market sentiment[47] - **Construction Process**: - Factors include manufacturing fixed asset investment completion amount, PPI YoY smoothed value, M2 YoY smoothed value, social financing YoY smoothed value, medium and long-term loan growth YoY smoothed value, market turnover rate, and margin balance percentile[48] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if indicator improves} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using the National Growth Index and National Value Index[48] - **Evaluation**: The factor captures the cyclical characteristics of value and growth styles[47] 2. Factor Name: Size Rotation Factor - **Construction Idea**: The factor is based on economic prosperity, liquidity, and market sentiment[55] - **Construction Process**: - Factors include manufacturing fixed asset investment completion amount, PPI YoY smoothed value, gold daily return rate, government bond yield, credit spread, M1 YoY smoothed value, market turnover rate, and margin balance percentile[56] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if indicator improves} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using the CSI 300 Index and CSI 1000 Index[57] - **Evaluation**: The factor captures the cyclical characteristics of large-cap and small-cap styles[55] Factor Backtest Results Value-Growth Rotation Factor - Annualized Return: 9.2%[51] - Benchmark Annualized Return: 1.7%[51] - Excess Annualized Return: 7.5%[51] - Monthly Win Rate: 60.2%[51] Size Rotation Factor - Annualized Return: 9.2%[59] - Benchmark Annualized Return: 0.1%[59] - Excess Annualized Return: 9.0%[59] - Monthly Win Rate: 58.3%[59] Industry Rotation Solution 1. Factor Name: Macro Factor - **Construction Idea**: The factor is based on the second-order changes in economic growth and liquidity[67] - **Construction Process**: - Factors include PMI, social financing scale, manufacturing fixed asset investment completion amount, CPI, M2 growth rate, 10-year government bond yield, and credit spread[70] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if indicator improves} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using industry indices[73] - **Evaluation**: The factor captures the marginal inflection points of macro trends[67] 2. Factor Name: Fundamental Factor - **Construction Idea**: The factor is based on historical prosperity, prosperity changes, and prosperity expectations[79] - **Construction Process**: - Factors include industry component stock median, industry profitability, and industry consensus profit expectations[79] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if indicator improves} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using industry indices[82] - **Evaluation**: The factor captures the core of industry prosperity[79] 3. Factor Name: Technical Factor - **Construction Idea**: The factor is based on index momentum, leading stock momentum, and K-line patterns[87] - **Construction Process**: - Factors include industry index relative excess return IR, leading stock sharp ratio, and K-line pattern score[89] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if indicator improves} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using industry indices[96] - **Evaluation**: The factor captures the technical evaluation of industry trends[87] 4. Factor Name: Crowding Factor - **Construction Idea**: The factor is based on financing inflows, turnover rate, and transaction proportion[100] - **Construction Process**: - Factors include industry financing buy amount, industry turnover rate, and industry transaction amount proportion[101] - Use the formula: $$ \text{Factor} = \begin{cases} 1 & \text{if indicator improves} \\ 0 & \text{otherwise} \end{cases} $$ - Backtest using industry indices[104] - **Evaluation**: The factor captures the crowding level of industries[100] Industry Rotation Backtest Results Macro Factor - Annualized Return: 42.9%[73] - Benchmark Annualized Return: -22.8%[73] - Excess Annualized Return: 65.7%[73] Fundamental Factor - Annualized Return: 11.3%[85] - Benchmark Annualized Return: 2.8%[85] - Excess Annualized Return: 8.5%[85] - IC Mean: 8.2%[85] Technical Factor - Annualized Return: 9.7%[97] - Benchmark Annualized Return: 2.8%[97] - Excess Annualized Return: 6.9%[97] - IC Mean: 8.2%[97] Crowding Factor - Annualized Return: -2.9

- The diffusion index model has been tracking out-of-sample performance for four years, with notable results in 2021 when momentum strategies captured industry trends, achieving excess returns of over 25% before a significant drawdown in September due to cyclical stock adjustments. In 2022, the strategy maintained stable returns with an annual excess return of 6.12%. However, in 2023, excess returns declined to -4.58%, and in 2024, a major drawdown occurred after September due to the model's focus on upward trends, missing rebound industries, resulting in an annual excess return of -5.82%[24][28] - The diffusion index model suggests allocating to industries such as non-bank finance, construction, and defense military, which showed significant week-on-week improvement in rankings. The top six industries based on diffusion index rankings as of October 24, 2025, are non-bank finance (0.988), banking (0.967), steel (0.952), communication (0.946), comprehensive (0.913), and non-bank finance (0.9)[25][26][27] - The GRU factor model, based on minute-level volume and price data processed through GRU deep learning networks, has shown strong performance in short cycles but weaker performance in long cycles. The model has been effective in capturing trading information since 2021, achieving significant excess returns. However, since February 2025, the model has faced challenges in generating excess returns due to market focus on thematic trading[31][37] - The GRU factor model ranks industries based on their GRU factor scores. As of October 24, 2025, the top six industries are non-bank finance (1.13), banking (1), electric power and utilities (0.54), textile and apparel (0.03), automotive (-0.58), and machinery (-0.73). Industries with the lowest GRU factor scores include food and beverage (-17.79), non-ferrous metals (-10.81), basic chemicals (-8.82), agriculture (-8.76), coal (-6.57), and building materials (-6.48)[6][13][32] - The GRU factor model's weekly industry rotation suggests allocating to non-bank finance, electric power and utilities, textile and apparel, transportation, steel, and petrochemicals. For the week ending October 24, 2025, the model achieved an average return of 1.89%, underperforming the equal-weighted return of the CSI first-tier industries by -0.77%. For October, the model's excess return is 1.80%, while the year-to-date excess return stands at -6.41%[6][34][39]

Core Insights - The report highlights the acceleration of industry rotation in the A-share market, indicating a shift from sustained single-line trends to rapid sector changes, with the industry rotation index showing increased activity since 2023 [13][14] - It emphasizes the scarcity of fundamentally strong investment opportunities, suggesting that while growth investment remains relevant, the range of viable options has significantly narrowed compared to the past two decades [20][19] - The report identifies the importance of "crowding" and "calendar effects" as tools for navigating the current market dynamics, with a focus on how these metrics can guide investment strategies [37][38] Group 1: Industry Rotation Dynamics - The A-share market has experienced a notable increase in industry rotation speed, with the duration of dominant trends decreasing from 6-12 months in previous years to approximately 2 months in 2023 [13][14] - The report outlines that the current market environment is characterized by a blend of "extreme rotation" and "absolute low volatility," where thematic investments and stable fundamental assets coexist [4][5] - The report provides a comparative analysis of industry performance, indicating that sectors such as military, robotics, and software are expected to benefit from low crowding and catalysts in the near term [6] Group 2: Investment Strategies and Sector Focus - For active funds, the report suggests focusing on sectors with strong growth trends and catalysts, particularly in the context of the upcoming quarterly reports [6] - It recommends maintaining positions in sectors like computing power, innovative pharmaceuticals, and non-ferrous metals, while also noting the potential for increased allocations in dividend-paying sectors such as banks and home appliances as the year-end approaches [6] - The report highlights the significance of calendar effects, suggesting that both active and long-term investors may find opportunities for positioning in the market during specific periods [5][6]

Quantitative Models and Construction Methods 1. Model Name: Stock Index Futures Timing Model - **Model Construction Idea**: The model uses the basis of stock index futures to reflect market sentiment changes and constructs daily frequency timing signals based on this correlation[7] - **Model Construction Process**: - The model groups and tests the correlation trend between the basis of stock index futures and the index itself - Constructs daily frequency timing signals based on this correlation - As of October 17, 2025, the timing signal based on the basis of the CSI 500 stock index futures remained at 1[31] - **Model Evaluation**: The model effectively captures market sentiment changes and provides timely signals for trading decisions[7] 2. Model Name: Multi-Dimensional Timing Model - **Model Construction Idea**: The model integrates macro, micro, meso, and derivative signals to form a four-dimensional non-linear timing model[33] - **Model Construction Process**: - The A-share market is divided into nine states based on macro, micro, and meso signals, each corresponding to long and short signals to form a three-dimensional large cycle timing signal - On this basis, the derivative signal generated by the basis of stock index futures is superimposed to form a four-dimensional non-linear timing model - The latest composite multi-dimensional timing signal is long (1)[34] - **Model Evaluation**: The model provides a comprehensive view of market conditions by integrating multiple dimensions, enhancing the accuracy of timing signals[33] 3. Model Name: Style Enhancement Model - **Model Construction Idea**: The model enhances returns by adding enhancement factors to the multi-style strategy, suppressing single-style fluctuations, and achieving stable excess returns in different cycles[41] - **Model Construction Process**: - The model is based on the multi-style strategy and adds enhancement factors - It dynamically adjusts the weights of different styles to achieve stable excess returns - As of October 17, 2025, the low volatility enhancement strategy achieved an excess return of 6.05%[42] - **Model Evaluation**: The model effectively enhances returns while controlling risks, providing stable performance across different market cycles[41] Model Backtesting Results Stock Index Futures Timing Model - **Absolute Return**: Not specified - **Excess Return**: 4.33%[9] - **Annualized Return**: Not specified - **Sharpe Ratio**: Not specified Multi-Dimensional Timing Model - **Absolute Return**: Not specified - **Excess Return**: 4.33%[9] - **Annualized Return**: Not specified - **Sharpe Ratio**: Not specified Style Enhancement Model - **Absolute Return**: Not specified - **Excess Return**: 6.05%[8] - **Annualized Return**: Not specified - **Sharpe Ratio**: Not specified Quantitative Factors and Construction Methods 1. Factor Name: High-Frequency Factor - **Factor Construction Idea**: The factor captures market valuation and sentiment risks using high-frequency data[11] - **Factor Construction Process**: - The factor uses high-frequency data to measure market depth, spread, and price elasticity - Constructs indicators such as average depth, spread, and price elasticity to reflect market liquidity and sentiment - For example, the average depth is calculated as: $$ avg_{depth} = \frac{av1 + bv1}{2} $$ where av1 and bv1 are the sell and buy volumes at the first level of the order book[98] - **Factor Evaluation**: The factor effectively captures market liquidity and sentiment changes, providing valuable insights for trading decisions[11] Factor Backtesting Results High-Frequency Factor - **Absolute Return**: Not specified - **Excess Return**: Not specified - **Annualized Return**: Not specified - **Sharpe Ratio**: Not specified Industry and ETF Rotation Strategy 1. Strategy Name: Industry Rotation Strategy - **Strategy Construction Idea**: The strategy uses quantitative fundamental drivers, quality low volatility style drivers, and distressed reversal industry discovery methods to construct an industry rotation strategy[76] - **Strategy Construction Process**: - Combines industry fundamental rotation, quality low volatility, and distressed reversal three-dimensional industry rotation strategies into an equal-weight portfolio - Selects industries from different dimensions to achieve factor and style complementarity, reducing the risk of a single strategy - As of October 17, 2025, the annualized excess return of the industry rotation strategy based on three-strategy integration was 10.59%, with a Sharpe ratio of 0.74[80] - **Strategy Evaluation**: The strategy effectively combines multiple dimensions to enhance returns while controlling risks, providing stable performance across different market cycles[76] Strategy Backtesting Results Industry Rotation Strategy - **Absolute Return**: Not specified - **Excess Return**: 14.75%[10] - **Annualized Return**: 10.59%[80] - **Sharpe Ratio**: 0.74[80]

Report Industry Investment Rating No information provided in the report regarding industry investment rating. Core Viewpoints of the Report - The US ETF market has seen the issuance of multiple asset - allocation products. The inflow of gold ETFs is significant, and precious - metal stock ETFs have performed significantly better than precious - metal ETFs. - In the US ordinary public - offering fund market, the outflow of domestic stock funds remains around $20 billion, while the inflow of bond products is stable, slightly exceeding $10 billion [3]. Summary by Relevant Catalog 1. US ETF Innovation Products: Multiple Asset - Allocation Products Issued - Last week, 22 new products were issued in the US, including various types such as downside protection, leverage, theme, allocation, and rotation products [6]. - There were 7 new downside protection products, including Calamos' laddered downside protection products linked to Bitcoin. Arrow Funds also issued a Bitcoin strategy product [6]. - 4 single - stock leverage products were issued, linked to Figma, Futu, JD.com, and Lemonade [7]. - GMO issued a dynamic asset - allocation ETF, with 40 - 80% invested in stocks and the rest in fixed - income and liquid alternative assets, based on GMO's 7 - year asset return forecast [7]. - AlphaDroid issued two strategy products, a momentum strategy and an industry rotation product [8]. - American Century issued 2 fundamental active ETFs, for small - cap value and small - cap growth [8]. - Pictet issued 3 stock ETFs, entering the US ETF market, with one using an AI strategy and two being theme products [8]. 2. US ETF Dynamics 2.1 US ETF Funds: Significant Inflow into Gold ETFs - In the past week, US ETFs maintained a high - speed inflow of nearly $50 billion, with domestic stocks inflowing over $25 billion and commodity ETFs mainly composed of gold also having a large inflow [9]. - The inflow of US broad - based stock products was stable last week, and the gold ETF GLD ranked second in the inflow of all products. Among bond products, comprehensive products had relatively more inflows, while high - yield bonds and alternative bond products had outflows [9]. 2.2 US ETF Performance: Precious - Metal Stock ETFs Significantly Outperform Precious - Metal ETFs - Due to frequent global situation changes this year, precious - metal ETFs led by gold have continuously risen significantly, and precious - metal - related stock ETFs such as gold - mining stocks have had significantly higher increases, with many products rising around 150% [3]. 3. Recent Capital Flows of US Ordinary Public - Offering Funds - In August 2025, the total amount of non - money public - offering funds in the US was $22.98 trillion, an increase of $0.41 trillion compared to July 2025. The S&P 500 rose 1.91% in August, and the scale of domestic stock products increased by 1.62%, with the redemption pressure easing [14]. - According to weekly ICI statistics, the outflow of US domestic stock funds last week remained around $20 billion, while the inflow of bond products was stable, slightly exceeding $10 billion [14].

- The diffusion index model tracks industry rotation based on momentum principles, focusing on upward trends in industry performance. It has been monitored for four years, with notable excess returns in 2021 (25% before September) and stable returns in 2022 (6.12%). However, it faced significant drawdowns in 2023 (-4.58%) and 2024 (-5.82%) due to market reversals. For October 2025, recommended industries include non-ferrous metals, banking, communication, steel, electronics, and automobiles[26][30] - The GRU factor model utilizes GRU deep learning networks to analyze minute-level volume and price data, aiming to capture industry rotation. It has shown strong adaptability in short cycles but struggles in long cycles and extreme market conditions. For October 2025, industries such as building materials, electric power and utilities, textiles and apparel, transportation, steel, and petrochemicals are recommended[33][36] - Diffusion index model weekly tracking shows top industries as non-ferrous metals (0.979), communication (0.931), banking (0.929), steel (0.849), electronics (0.833), and electric power equipment & new energy (0.816). Industries with the largest weekly changes include consumer services (0.271), coal (0.251), and retail trade (0.127)[27][28][29] - GRU factor weekly tracking highlights top industries as textiles and apparel (4.22), comprehensive (2.68), transportation (2.16), steel (2), electric power and utilities (1.84), and petrochemicals (1.08). Industries with the largest weekly improvements include food and beverage, electric power and utilities, and real estate[34][37] - Diffusion index model performance: weekly average return -3.42%, excess return over equal-weighted industry index -0.85%, October excess return -1.21%, year-to-date excess return 3.42%[30] - GRU factor model performance: weekly average return -1.74%, excess return over equal-weighted industry index 0.86%, October excess return 2.51%, year-to-date excess return -5.40%[36]