1. OpenClaw的典型使用场景：构建策略并进行信号提示 前期，我们尝试过应用OpenClaw进行从提取数据到构建不同类型的量化策略尝试，从流程上来说，OpenClaw自主部署量化环境、提取数据到测算量化策略是可行的，但考虑到 OpenClaw可以进行市场跟踪、执行定时任务，可以完整的执行一系列流程化的动作，这些工作更能体现出OpenClaw与其他平台的差异，因此，本文尝试使用OpenClaw来构建 定投策略和基于该定投策略的信号定时提示系统。 本文的OpenClaw部署于云服务器，通讯软件以飞书进行，数据以API的形式读取Tushare的数据库，实现OpenClaw直接读取数据进行完整的策略构建。本次所有与OpenClaw的 沟通都只通过飞书来实现，可以实现使用碎片化的时间一步步完成相关策略。 因此在下文一些OpenClaw的相应展示，我们直接贴出一些飞书的对话截图，以展示双方的对话过程。 2. 使用OpenClaw进行定投策略构建 2.1 准备工作：数据提取 首先，我们仍然是读取较为完整的指数数据保存在本地，后续的计算都以本地保存数据来进行。 OpenClaw可以实现从提取数据到定投策略构建再到策略的 ...

1．情绪模型观点：投资者情绪本周震荡转弱 市场情绪转弱： 截至 3 月 20 日，市场情绪指标数值为 1.7 ，较上周五的 1.55 有所上升，情绪指标周内震荡为主，从情绪角度来看，模型观点偏中性。从分项指标的变化来 看，本周多项细分指标与上周相比有所下降，受外部政治风险的持续影响，需关注市场情绪进一步回落的情况。 | 表 1: 市场结构化情绪指标概况 | | | | --- | --- | --- | | 指标简称 | 含义 | 情绪指示方向 | | 行业间交易波动率 | 资金在各板块间的交易活跃度 | 正向 | | 行业交易拥挤度 | 极值状态判断市场是否过热 | 负向 | | 价量一致性 | 资金情绪稳定性 | 正向 | | 科创 50 成交占比 | 资金风险偏好 | 正向 | | 行业涨跌趋势性 | 刻画市场轮涨补涨程度,趋势衡量 | 正向 | | િટી | 价格体现买方和卖方力量相对强弱 | 正向 | | 主力买入力量 | 主力资金净流入水平 | 正向 | | PCR 结合 VIX | 从期权指标看市场多空情绪 | 正向或负向 | | 融资余额占比 | 资金对当前和未来观点多空 | 正向 | | ...

Core Insights - The article discusses the performance differences among various growth indices, highlighting a significant annualized return gap of up to 31.62% over the past five years among different indices [5][9]. - It emphasizes the varying definitions of growth factors by three index companies (China Securities Index, Guotai Junan Index, and Huazheng Index), which impacts the performance of their respective growth indices [9][12]. Performance Analysis - The highest annualized return among growth indices is 22.46% for the Growth Trend 100 index, while the worst-performing index has an annualized return of -9.16% [9][34]. - The article categorizes growth indices into four main types: broad-based + growth, pure SmartBeta growth, composite SmartBeta growth, and industry-themed + growth [9][12]. Index Effectiveness - The article identifies that the Sci-Tech Innovation Board and the ChiNext Board are suitable for using growth-enhanced strategies, showing higher average gains during favorable periods and lower losses during downturns [27][28]. - Small-cap indices combined with growth factors demonstrate a high cost-performance ratio, with annualized excess returns of 2.63% during favorable periods compared to -2.12% during unfavorable periods [27][28]. Long-term Performance - The standard growth index has shown superior long-term performance, making it a primary choice for adding growth factors in large-cap indices, with an annualized excess return of 6.77% since 2019 [27][28]. - In the mid-cap space, the 500 Trend Growth Index has outperformed, with an annualized excess return of 12.91% since 2017 [27][28]. Notable Growth Indices - Some growth indices that have performed well over both short and long terms include Dongzheng Advantage Growth (18.25% annualized return over ten years) and A-share Growth Pioneer 50 (21.67% annualized return over ten years) [34][35]. - The article suggests that indices utilizing consistent expectations can balance performance across different time frames, indicating their long-term allocation value [34][35]. Classification of Growth Indices - The article employs cluster analysis to categorize growth indices into seven types, including micro-cap growth, small-cap growth, high elasticity growth, large-cap growth, industry growth, value growth, and stable growth [3][36]. - It highlights the low correlation among different growth sub-strategy indices, suggesting the potential for constructing multi-strategy portfolios to enhance returns [3][36].

Key Points - The article discusses the construction and application of chip structure in stock selection, emphasizing the importance of understanding investor behavior and the distribution of funds at different price levels [2][6][19]. - It highlights the dynamic nature of chip costs, which are influenced by both buying and selling behaviors, and the necessity of detailed micro-trading data for accurate calculations [4][7]. - The analysis of chip structure allows for the identification of potential support and resistance levels in stock prices, providing a richer set of information compared to traditional volume-price factors [6][18]. Chip Average Cost Construction and Application - The construction of chip average cost involves calculating the weighted average cost of historical chips to depict the current market's average holding cost [8][9]. - A higher indicator value indicates that the historical average cost is above the current stock price, suggesting a floating loss for the market, while a lower value indicates a floating profit [9][10]. Improvement of Chip Structure Based on Fund Classification - Traditional methods of chip construction do not differentiate between different types of investors, which can obscure important behavioral information [19][20]. - By introducing fund flow data from institutions and retail investors, the article proposes a more nuanced approach to constructing chip distribution and weighted cost indicators for different investor types [19][21]. - The method shows slight improvements in factor IC and monotonicity of grouped returns, although the overall enhancement is limited [20][22]. Factor Synthesis and Performance Analysis - The article discusses the complementary relationship between the institutional-retail chip cost difference factor and traditional chip cost factors, suggesting that one contributes to predictive strength while the other enhances ranking stability [31][32]. - The synthesized chip factor achieves an IC mean of 4.35%, outperforming traditional volume-based chip factors and showing improved stability in multi-group performance [32][35]. - The performance of the synthesized factor varies significantly across different market capitalization segments, with better results observed in small to mid-cap stocks compared to large-cap stocks [41][42]. Market Capitalization Domain Results - The synthesized factor demonstrates stronger predictive capabilities in small-cap stocks, where investor behavior is more aligned with trading strategies that involve high turnover and profit-taking [45][46]. - Adjustments to the factor application in the mid-cap segment have led to improved performance, indicating the importance of tailoring strategies to specific market conditions [43][44].

Core Viewpoint - The article discusses the construction of two strategies based on Return on Equity (ROE) stability and improvement, emphasizing the importance of selecting high-quality stocks with stable ROE for investment opportunities [2][29]. ROE Stability Strategy Construction - A study was conducted on the ROE transition matrix from April 30, 2010, to April 30, 2024, categorizing stocks into six groups based on their ROE levels, with subsequent annual returns and the proportion of stocks remaining in each ROE range analyzed [4][32]. - The analysis revealed that stocks with an ROE between 10% and 15% had a 46.47% chance of remaining in that range the following year, while those with high ROE levels showed a higher likelihood of decline compared to improvement [5][6]. - The study identified four financial dimensions to characterize stability: profitability stability, growth stability, leverage stability, and cash flow stability, with specific factors selected from each dimension [9][10]. - A high ROE stock pool was created by filtering stocks with a historical ROE of at least 10% over the past nine quarters, resulting in approximately 600 stocks being selected for further analysis [11][14]. - The stability factor significantly improved the proportion of stocks maintaining high ROE, with the highest stability group (G1) showing an 83.20% retention rate for high ROE [14][19]. ROE Improvement Strategy Construction - The article also explores the historical momentum effect of ROE improvement, indicating that stocks with ROE increases over the past one, two, or three years had probabilities of continued improvement of 44.03%, 41.83%, and 42.05%, respectively [33]. - A three-step process was introduced to filter stocks expected to improve ROE based on analyst forecasts, resulting in an average selection of 163 stocks with a success rate of 70.98% [35][39]. - The ROE improvement strategy was constructed from the filtered stock pool, with a backtest period from December 31, 2013, to February 28, 2026, yielding an annualized return of 22.35% compared to 14.31% for the stock pool [43][44].

Core Viewpoint - The development of AI has significantly enhanced the efficiency of quantitative work, evolving through three stages: initial challenges with data processing, rapid coding assistance, and the introduction of OpenClaw for streamlined strategy construction and execution [1][2][3][4]. Group 1: AI's Impact on Quantitative Research - AI has opened new investment strategy methodologies, including machine learning, while also improving traditional multi-factor and fundamental quantitative frameworks [1]. - The first stage of AI in quantitative research faced challenges due to data hallucinations from large models, making precise data processing difficult [1]. - In the second stage, AI's coding capabilities evolved rapidly, allowing quantitative researchers to quickly generate code and optimize existing code, significantly enhancing work efficiency [2]. - The third stage introduced OpenClaw, which autonomously handles the quantitative work environment and data extraction, potentially allowing users to construct and backtest strategies with minimal coding knowledge [3][4]. Group 2: OpenClaw Deployment and Functionality - OpenClaw can be deployed on cloud servers or local machines, with considerations for hardware capabilities and security [6][7]. - The integration of data APIs into OpenClaw represents a significant efficiency boost, although challenges remain with the quality and cost of data sources [8]. - OpenClaw autonomously installs necessary libraries and configurations for quantitative analysis, streamlining the setup process [9][12]. Group 3: Strategy Construction and Testing - OpenClaw can facilitate simple quantitative strategy testing based on user ideas, such as backtesting a strategy involving stocks that experience consecutive price increases [15][16]. - The performance of various strategies, including those based on consecutive price increases and decreases, has been analyzed, revealing different profitability characteristics [18][22]. - OpenClaw successfully generated a comprehensive factor table for the CSI 500 index, demonstrating its capability in multi-factor quantitative stock selection [30][31]. Group 4: Machine Learning Strategy Development - OpenClaw has been utilized to develop machine learning strategies, such as a GRU model, showcasing its potential for automating complex quantitative tasks [40][44]. - The feature engineering process for the GRU model was effectively executed, resulting in a substantial dataset for training [45]. Group 5: Challenges and Limitations - Despite advancements, OpenClaw still faces issues such as slow response times, misunderstanding of commands, and occasional failures in executing tasks correctly [48][53]. - The need for improved data extraction efficiency and error correction during calculations has been identified as critical for enhancing user experience [39][54].

Group 1 - The core viewpoint of the article highlights the increase in the issuance of thematic ETFs in the US, with 10 new products launched last week, indicating a growing trend in innovative ETF offerings [2][3] - Notable new products include the Avos Global Equities ETF, 21Shares Polkadot ETF, and Roundhill Space & Technology ETF, which reflect diverse investment themes [2][3] - The article emphasizes the performance of active management strategies, particularly MFS's new emerging markets ETF that combines quantitative and qualitative selection methods [3] Group 2 - Recent data shows a significant outflow from domestic equity ETFs, with over $14 billion withdrawn in the week of February 18-25, while international equity products saw inflows exceeding $8 billion [4][11] - The article notes that commodity ETFs are experiencing outflows, while bond products continue to attract investments, indicating a shift in investor preferences [4][8] - The performance of futures strategies has been highlighted, with certain products achieving returns close to 10% this year, showcasing the effectiveness of commodity-focused strategies [10] Group 3 - The article provides insights into the top inflows and outflows of ETFs, with the iShares 0-3 Month Treasury Bond ETF seeing a net inflow of $29.82 billion, while the SPDR S&P 500 ETF experienced a significant outflow of $112.12 billion [8] - Vanguard products have shown stable inflows, contrasting with the notable outflows from the SPDR S&P 500 ETF, indicating varying investor confidence across different fund families [9]

Group 1 - Investor sentiment has been declining throughout the week, with the market sentiment indicator dropping to 1.40 from 1.85, indicating a neutral to bearish outlook [4][5][8] - The industry trading volatility has been rising, suggesting increased sector rotation, while the price-volume consistency indicator has slightly decreased, reflecting a neutral sentiment overall [8][12][16] - The average daily trading volume for the entire A-share market decreased by 26.52% to 17,932.48 billion, indicating reduced market activity compared to the previous week [12][14] Group 2 - The short-term scores for industries such as utilities, oil and petrochemicals, coal, environmental protection, and transportation are leading, with utilities scoring 100, indicating strong short-term performance [31][32] - The model indicates that the banking sector's short-term score is rising, and both value and large-cap styles are currently favored [31][40] - The correlation between industry congestion and weekly price changes is low at 0.39, suggesting that high congestion sectors like oil and petrochemicals are experiencing significant price increases, while low congestion sectors like retail and real estate may have better long-term value [35][38]

Core Viewpoint - The article discusses the performance and construction of four quantitative strategies: dividend, quality, growth, and value, highlighting their monthly and year-to-date performance metrics for February 2026. Group 1: Quantitative Strategy Monthly Performance Tracking - The dividend strategy achieved an absolute return of 0.16% in February 2026, underperforming the CSI Dividend Total Return Index by 2.18%. Year-to-date, it recorded a 9.46% absolute return, outperforming the index by 3.28% [5][8]. - The quality strategy had an absolute return of 2.12% in February 2026, exceeding the CSI Quality Total Return Index by 2.57%. For the year-to-date, it posted an 11.30% absolute return, outperforming the index by 9.20% [5][8]. - The growth strategy, with a 90% allocation, achieved an absolute return of 5.13% in February 2026, outperforming the Taibao Active Equity Growth Fund by 2.91%. Year-to-date, it recorded a 15.80% absolute return, exceeding the fund by 5.56% [5][8]. - The value strategy posted an absolute return of 2.02% in February 2026, slightly outperforming the Guoxin Value Total Return Index by 0.29%. However, year-to-date, it had a 6.55% absolute return, underperforming the index by 3.83% [6][8]. Group 2: Strategy Construction Methodology - The dividend strategy is constructed in two steps: first, selecting stocks expected to have increased dividends in the next year from various dimensions; second, applying multi-factor optimization to finalize the dividend portfolio [9]. - The quality strategy involves three steps: first, screening for stocks with a historical ROE of at least 10% over the past nine quarters; second, constructing stability factors based on profitability, growth, and leverage; third, scoring stocks based on growth, volatility, long-term momentum, and dividends to finalize the quality portfolio [11]. - The growth strategy is built in three steps: first, selecting the top 50 stocks based on analyst consensus profit growth; second, optimizing for stocks with the highest upward revisions in profit expectations; third, applying an industry rotation model to weight stocks in favorable sectors [14]. - The value strategy is constructed in two steps: first, selecting high ROE stocks with stable future expectations; second, optimizing for 50 stocks based on valuation factors to avoid value traps [18].

Group 1 - The core viewpoint of the article emphasizes the recovery of the manufacturing sector, which boosts expectations for the industrial non-ferrous metals market, driven by policy support and improved supply-demand structure [1][2] - The Ministry of Industry and Information Technology, along with seven other departments, issued a work plan for the non-ferrous metals industry, targeting an average annual growth of around 5% in industry value added and a breakthrough of 20 million tons in recycled metal production by 2025-2026 [1][3] - The industrial non-ferrous metals inventory remains low, with LME copper and aluminum stocks at historical lows, supporting price stability amid a cyclical economic recovery [4][5] Group 2 - Prices of copper and aluminum have been on the rise over the past three years, reflecting a significant recovery in the industrial non-ferrous metals market, driven by increased demand from overseas manufacturing and infrastructure investments in emerging economies [5][11] - The rapid development of emerging industries, such as industrial and service robots, is driving demand for key materials like aluminum and copper, with domestic industrial robot production expected to grow by 38.95% year-on-year in 2025 [8][11] - The expansion of the new energy vehicle industry is also contributing to the rising demand for aluminum and copper, with production expected to increase by 23.26% year-on-year in 2025 [11][14] Group 3 - The Shanghai Futures Exchange's non-ferrous metals index differs fundamentally from stock indices, as it tracks the prices of standardized futures contracts for metals like copper and aluminum, reflecting direct supply-demand relationships [17][20] - The futures index is based on a limited number of metal contracts, ensuring it effectively represents the core non-ferrous metals sector, while stock indices include a broader range of companies across the non-ferrous metals industry [18][22] - The futures index's performance is closely tied to commodity price fluctuations, while stock indices are influenced by a variety of factors, including company performance and market sentiment [38][40]