- The report discusses two main quantitative models: the Diffusion Index Model and the GRU Factor Model[6][7][14][33] Diffusion Index Model 1. **Model Name**: Diffusion Index Model 2. **Model Construction Idea**: The model is based on the principle of price momentum, capturing industry trends by observing the diffusion index of various sectors[6][27] 3. **Model Construction Process**: - Calculate the diffusion index for each industry - Rank industries based on their diffusion index values - Select top industries for investment based on their diffusion index rankings - Formula: $ \text{Diffusion Index} = \frac{\text{Number of advancing stocks}}{\text{Total number of stocks}} $ 4. **Model Evaluation**: The model has shown varying performance over the years, with significant returns in some periods and notable drawdowns in others[26][30] 5. **Model Test Results**: - 2025 YTD excess return: -3.16%[25] - April 2025 excess return: -1.08%[30] - Weekly excess return: 0.43%[30] GRU Factor Model 1. **Model Name**: GRU Factor Model 2. **Model Construction Idea**: The model leverages GRU (Gated Recurrent Unit) deep learning networks to analyze minute-level price and volume data, aiming to capture trading information and trends[7][33] 3. **Model Construction Process**: - Collect minute-level price and volume data - Train a GRU network on historical data to identify patterns - Rank industries based on GRU factor scores - Select top industries for investment based on their GRU factor rankings - Formula: $ \text{GRU Factor} = \text{GRU Network Output} $ 4. **Model Evaluation**: The model has shown strong performance in short cycles but may struggle in long cycles or extreme market conditions[33][36] 5. **Model Test Results**: - 2025 YTD excess return: -3.33%[33] - April 2025 excess return: 0.92%[36] - Weekly excess return: -0.31%[36] Factor Rankings and Performance 1. **Diffusion Index Rankings (as of April 25, 2025)**: - Top industries: Banking (0.986), Non-Banking Financials (0.948), Comprehensive Financials (0.926), Computers (0.873), Retail (0.847), Communication (0.841)[14][27] - Bottom industries: Coal (0.105), Oil & Petrochemicals (0.175), Food & Beverage (0.257), Agriculture (0.396), Steel (0.423), Utilities (0.491)[27][28] 2. **GRU Factor Rankings (as of April 25, 2025)**: - Top industries: Banking (3.81), Transportation (2.77), Non-Banking Financials (2.37), Textiles & Apparel (2.34), Media (1.98), Light Manufacturing (1.81)[7][34] - Bottom industries: Automobiles (-5.31), Agriculture (-4.05), Pharmaceuticals (-4.03), Home Appliances (-3), Coal (-2.67), Defense (-2.64)[34] Weekly and Monthly Performance 1. **Diffusion Index Weekly Performance**: - Top weekly gainers: Construction (0.189), Real Estate (0.187), Building Materials (0.136), Light Manufacturing (0.089), Textiles & Apparel (0.081), Communication (0.069)[29] - Top weekly losers: Steel (-0.111), Utilities (-0.038), Non-Ferrous Metals (-0.018), Coal (0.003), Transportation (0.007), Computers (0.009)[29] 2. **GRU Factor Weekly Performance**: - Top weekly gainers: Banking, Textiles & Apparel, Consumer Services[34] - Top weekly losers: Coal, Automobiles, Construction[34]

Group 1 - The article emphasizes that the economic data validates the previously low expectations, indicating limited room for further downward adjustments [3] - The article discusses the potential for a strategic opportunity shift, with expectations for a comprehensive bull market by 2026 [7] - The article highlights the impact of U.S. tariffs on China, suggesting that the threat may dampen risk appetite, particularly with a sensitive window in Q2 2025 [8] Group 2 - The pharmaceutical sector has experienced four consecutive years of negative returns, but there is a significant probability of a sector rotation reversal in 2025 [9] - The article notes that while short-term sentiment indicators are high, overall market liquidity has not reached previous peaks, suggesting a cautious long-term outlook amidst rising technology industry trends [11] - The article outlines a cautious investment strategy for U.S. stocks, recommending hedging and timely profit-taking during potential rebounds, particularly in the tech sector [14]

金工研究 杠铃两端表现不稳定性加剧， 消费板块资金情绪升温 —— 量化市场追踪周报（2025W11） 请阅读最后一页免责声明及信息披露 http://www.cindasc.com 1 [Table_ReportTime] 2025 年 3 月 16 日 证券研究报告 [Table_ReportType] 金工定期报告 [Table_Author] 于明明 金融工程与金融产品 首席分析师 执业编号：S1500521070001 联系电话：+86 18616021459 邮 箱：yumingming@cindasc.com 吴彦锦 金融工程与金融产品 分析师 执业编号：S1500523090002 联系电话：+86 18616819227 邮 箱：wuyanjin@cindasc.com 周君睿 金融工程与金融产品 分析师 执业编号：S1500523110005 联系电话：+86 19821223545 邮 箱：zhoujunrui@cindasc.com [Table_Title] 量化市场追踪周报(2025W11)：杠铃两端表现不稳 定性加剧，消费板块资金情绪升温 [Table_ReportDate] 20 ...

Summary of Key Points from the Conference Call Industry or Company Involved - The conference call focuses on the **AI investment strategies** and **ETF market** in the context of the **capital market** as discussed by **Huatai Securities** during their **2025 Spring Strategy Meeting**. Core Points and Arguments - **AI Strategies in Investment**: AI strategies significantly enhance traditional multi-factor models by processing vast amounts of data and complex factors, particularly in volume and price data analysis, optimizing investment decisions [1][4][9]. - **Acceptance of AI in Asset Management**: The asset management industry is increasingly accepting AI strategies, particularly those based on statistical models, due to their strong performance. However, the ability of reasoning-based large language models to reach expert-level performance remains to be validated [1][13][14]. - **ETF Market Growth**: The ETF market has surpassed **3.8 trillion yuan**, with a focus on smart beta strategies to achieve stable returns through industry rotation and asset allocation models [1][22]. - **Investment Strategy Focus**: Huatai Securities emphasizes a robust return strategy, primarily focusing on bond investments, and utilizes global asset allocation models and qualitative analysis for market judgment [1][27]. - **Industry Rotation Strategy**: The industry rotation strategy combines macro, meso, and micro factors with AI identification and qualitative analysis, favoring technology, consumer, and pharmaceutical sectors while adjusting investment targets based on significant events like the Two Sessions [3][31]. - **AI's Role in Financial Engineering**: AI enhances traditional multi-factor frameworks by integrating diverse data types, leading to more precise and efficient data analysis, thus optimizing portfolio design and improving returns while reducing risks [7][18]. - **Performance of AI in Quantitative Investment**: AI strategies outperform traditional multi-factor methods by effectively aggregating information and conducting global analyses, leading to superior excess returns [9][12]. - **Future of Large Models in Finance**: Large models like DeepSeek and ChatGPT show potential in subjective analysis, suggesting a new paradigm of combining subjective and quantitative investment approaches, although their expert-level capabilities need further validation [11][15]. - **ETF Product Development**: Huatai Securities is committed to providing ETF products and solutions, focusing on smart beta strategies and offering professional services, including market reports and strategy analyses [1][23]. Other Important but Possibly Overlooked Content - **Historical Context of AI in Quantitative Investment**: The application of AI in quantitative investment began around 2003, evolving through various phases, with significant adoption starting in 2017, leading to substantial investment returns [2][13]. - **Impact of Two Sessions on Market**: The analysis of the Two Sessions' impact on the market involves reviewing historical key topics and market performance, indicating that different time periods around the event affect market dynamics [32]. - **Investment Heat and Valuation Levels**: The current investment heat in AI-related sectors is at historical highs, with significant trading activity and valuation levels, necessitating cautious investment strategies [62][64]. - **Differentiation of Index Products**: Index products vary significantly in valuation levels and stock resonance, suggesting that investors should choose based on their risk appetite and investment strategy [68][70]. - **Performance of Active Equity Fund Managers**: Different fund managers exhibit varying performance in the AI sector, categorized into stable allocation, focused sector, and flexible adjustment types, highlighting the importance of selecting managers based on their stability and risk-return profile [73][74]. This summary encapsulates the essential insights from the conference call, providing a comprehensive overview of the discussions surrounding AI investment strategies and the ETF market.

Core Insights - The report highlights that the power equipment, real estate, and banking sectors present a favorable risk-return profile [1] - The report emphasizes the importance of monitoring industry rotation through volume indicators and crowding risk assessments [4][5] Industry Rotation Perspective 1: Volume Indicators - The core logic suggests that an increase in trading volume indicates a divergence in market opinions, potentially signaling a trend reversal [9] - In December 2022 and January 2023, most industries showed negative turnover rate slopes, while February 2023 saw a positive trend, particularly in the computer and power equipment sectors [10] - Industries with buy signals based on volume include power equipment, real estate, beauty care, agriculture, pharmaceuticals, and banking [10][11] Industry Rotation Perspective 2: Crowding Risk Indicators - The crowding indicator reflects the degree of trading activity overheating, serving as a warning for potential risks [13] - Industries at risk due to high transaction concentration include machinery, computers, and home appliances [13][14] Volume Buy Signal Industry Details and ETFs Power Equipment - The power equipment sector shows strong market attractiveness with a notable volume performance [19] - The crowding level is acceptable, with some companies driving volume without affecting the entire sector [19] - Relevant ETFs include those tracking solar power leaders and new energy indices [20] Real Estate - The real estate sector ranks in the middle for volume performance, with a relatively low crowding level indicating a good risk-return profile [24] - Relevant ETFs track indices such as mainland real estate and the full index of real estate [26] Beauty Care - The beauty care sector ranks in the middle for volume, with a high internal sentiment concentration indicating a favorable risk-return profile [29] Agriculture - The agriculture sector ranks high in volume performance, with a good risk-return profile due to low crowding levels [32] - Relevant ETFs track indices related to modern agriculture and livestock [33] Pharmaceuticals - The pharmaceutical sector ranks high in volume performance, with a good risk-return profile as well [36] - Relevant ETFs include those tracking various pharmaceutical indices [38] Banking - The banking sector ranks low in volume performance but shows a good risk-return profile with low crowding levels [43] - Relevant ETFs track indices such as the China Securities Banking Index [45]

证券研究报告 金工 遗传规划超额屡创新高，积极把握股 市结构性机会——春季量化观点 华泰研究 2025 年 2 月 19 日│中国内地 专题研究 中期建议积极把握股市结构性机会，短期建议参考遗传规划模型的信号 中期来看，建议积极把握股市结构性机会。一方面，国内增长市场预期指数 不一定跟随全球经济周期下行，存在逆势上行的可能性，中国股票资产有望 成为全球经济周期下行的"避风港"。另一方面，关键领域技术的突破、政 策对民营经济的支持，或持续提振市场参与者的信心，中国股票资产的价值 重估有望乘势而上。"科技+红利"或是进可攻、退可守的组合。在增长预期 指数趋势明朗之前，以景气动量为代表的自上而下行业轮动模型或依然无法 提供有效的投资建议，而以遗传规划为代表的自下而上行业轮动模型超额收 益已屡创新高。短期来看，我们建议投资者参考遗传规划模型的信号。 景气动量模型：自上而下行业轮动的代表，名副其实的 Smart Beta 景气动量模型从宏观、中观、微观三个视角，分别使用宏观因子、产业链数 据、财报和分析师一致预期数据，对行业 Δg 开展建模，月频调仓，是自上 而下行业轮动的代表。模型表现对市场风格的依赖度较高，尤其跟成 ...