Report Title - The report is titled "Commodity Quantitative CTA Weekly Tracking" by Guotou Futures [1] Core View - The proportion of long and short positions in commodities has changed little this week. The short positions in the non - ferrous sector have increased, and there are local long signals in the chemical and agricultural product sectors. The cross - sectionally strong sectors are agricultural products and chemicals, while the non - ferrous sector is weak. The overall signal for methanol is neutral, for float glass is long, and for lead is short [3][5][8][9] Industry Investment Rating - Not provided in the report Detailed Summaries Commodity Sector Analysis - **Non - ferrous Sector**: Momentum is marginally declining, short positions are increasing,持仓量 is decreasing, and cross - sectional differentiation is narrowing. Zinc and nickel are relatively weak. Gold's time - series momentum has stabilized, but the trading volume of Shanghai silver continues to rise, and intra - sector differentiation may widen [3] - **Black Sector**: The overall position factor is marginally declining, and the term structure differentiation is narrowing [3] - **Energy and Chemical Sector**: Cross - sectional momentum is differentiated. Ethylene glycol is cross - sectionally strong, while styrene is weak [3] - **Agricultural Product Sector**: The position of oils and fats has slightly declined [3] Factor Performance - **Last Week's and Current Month's Returns**: For the supply factor, last week's return was - 0.03% and the current month's return was - 0.09%; for the demand factor, last week was 0.00% and the current month was - 0.65%; for the inventory factor, last week was 0.02% and the current month was 1.00%; for the spread factor, last week was 0.00% and the current month was 0.35%; the cumulative return of major categories last week was - 0.03% and the current month was - 0.95% [4] Strategy Net Value and Fundamental Factors - **Methanol**: Last week, the supply factor weakened by 0.03%, the inventory factor increased by 0.02%, and the synthetic factor decreased by 0.03%. This week's comprehensive signal is neutral. On the fundamental side, the supply is bearish, demand is bearish, inventory is bullish but weakening, and the spread is bullish [5] - **Float Glass**: Last week, the supply factor strengthened by 1.47%, the demand factor increased by 1.58%, the inventory factor increased by 1.47%, the spread factor weakened by 0.04%, and the synthetic factor increased by 1.04%. This week's comprehensive signal is long. Supply is neutral, demand is neutral, inventory is bullish, and the spread is neutral - bearish [8] - **Lead**: Last week, the supply factor strengthened by 0.52%, the demand factor weakened by 0.40%, the inventory factor strengthened by 0.56%, the spread factor strengthened by 0.51%, and the synthetic factor strengthened by 0.32%. This week's comprehensive signal remains short. Supply is bearish, demand is bullish, inventory is bearish, and the spread is bearish [9] Factor Intensity and Momentum Indicators - **Factor Intensity**: For different factors such as supply, demand, inventory, and spread, their intensities vary in different commodities and time periods (last week and the current week) [4][8][9] - **Momentum Indicators**: Different sectors (black, non - ferrous, energy and chemical, agricultural products, equity index, and precious metals) have different values for momentum time - series, momentum cross - section, term structure, and position indicators [6]

Quantitative Models and Construction 1. Model Name: GRU Model - **Model Construction Idea**: The GRU model integrates fundamental and technical features to predict stock performance[3][19] - **Model Construction Process**: The GRU model is a recurrent neural network (RNN) variant designed to handle sequential data. It uses gating mechanisms to control the flow of information, allowing it to capture temporal dependencies in financial data. Specific details on the input features or training process are not provided in the report[3][19] - **Model Evaluation**: The GRU model shows mixed performance, with significant drawdowns in certain market segments[3][19] 2. Model Name: Barra1d - **Model Construction Idea**: A short-term factor model based on the Barra framework, focusing on daily data[3][19] - **Model Evaluation**: Barra1d exhibits significant drawdowns in multiple market segments, indicating weaker performance[3][19] 3. Model Name: Barra5d - **Model Construction Idea**: A medium-term factor model based on the Barra framework, focusing on 5-day data[3][19] - **Model Evaluation**: Barra5d demonstrates strong performance, achieving positive returns in various market segments[3][19] 4. Model Name: Close1d - **Model Construction Idea**: A short-term model focusing on daily closing prices[3][19] - **Model Evaluation**: Close1d performs well in certain market segments, achieving positive returns[3][19] 5. Model Name: Open1d - **Model Construction Idea**: A short-term model focusing on daily opening prices[3][19] - **Model Evaluation**: Open1d shows weaker performance, with significant drawdowns in certain market segments[3][19] --- Model Backtesting Results 1. GRU Model - **Weekly Excess Return**: -0.08% to -0.54% relative to the CSI 1000 Index[7][30] 2. Barra1d - **Weekly Excess Return**: -0.54%[31] - **Year-to-Date Excess Return**: 3.75%[31] 3. Barra5d - **Weekly Excess Return**: -0.31%[31] - **Year-to-Date Excess Return**: 7.42%[31] 4. Close1d - **Weekly Excess Return**: -0.40%[31] - **Year-to-Date Excess Return**: 5.73%[31] 5. Open1d - **Weekly Excess Return**: -0.08%[31] - **Year-to-Date Excess Return**: 6.68%[31] --- Quantitative Factors and Construction 1. Factor Name: Beta - **Factor Construction Idea**: Measures historical beta to capture market sensitivity[15] 2. Factor Name: Market Capitalization - **Factor Construction Idea**: Logarithm of total market capitalization[15] 3. Factor Name: Momentum - **Factor Construction Idea**: Average historical excess returns[15] 4. Factor Name: Volatility - **Factor Construction Process**: $ Volatility = 0.74 * \text{Historical Excess Return Volatility} + 0.16 * \text{Cumulative Excess Return Deviation} + 0.1 * \text{Residual Return Volatility} $ - **Parameters**: - Historical Excess Return Volatility: Measures the standard deviation of excess returns - Cumulative Excess Return Deviation: Captures deviations in cumulative returns - Residual Return Volatility: Measures the volatility of residual returns[15] 5. Factor Name: Nonlinear Market Capitalization - **Factor Construction Idea**: Cubic transformation of market capitalization[15] 6. Factor Name: Valuation - **Factor Construction Idea**: Inverse of price-to-book ratio[15] 7. Factor Name: Liquidity - **Factor Construction Process**: $ Liquidity = 0.35 * \text{Monthly Turnover} + 0.35 * \text{Quarterly Turnover} + 0.3 * \text{Annual Turnover} $ - **Parameters**: - Monthly Turnover: Measures trading activity over a month - Quarterly Turnover: Measures trading activity over a quarter - Annual Turnover: Measures trading activity over a year[15] 8. Factor Name: Profitability - **Factor Construction Process**: $ Profitability = 0.68 * \text{Analyst Forecast Earnings Yield} + 0.21 * \text{Inverse Price-to-Cash Flow} + 0.11 * \text{Inverse Price-to-Earnings (TTM)} $ $ + 0.18 * \text{Analyst Long-Term Growth Forecast} + 0.11 * \text{Analyst Short-Term Growth Forecast} $ - **Parameters**: - Analyst Forecast Earnings Yield: Measures expected earnings relative to price - Inverse Price-to-Cash Flow: Captures cash flow efficiency - Analyst Growth Forecasts: Reflects expected growth rates[15] 9. Factor Name: Growth - **Factor Construction Process**: $ Growth = 0.24 * \text{Earnings Growth Rate} + 0.47 * \text{Revenue Growth Rate} $ - **Parameters**: - Earnings Growth Rate: Measures growth in earnings - Revenue Growth Rate: Measures growth in revenue[15] 10. Factor Name: Leverage - **Factor Construction Process**: $ Leverage = 0.38 * \text{Market Leverage} + 0.35 * \text{Book Leverage} + 0.27 * \text{Debt-to-Asset Ratio} $ - **Parameters**: - Market Leverage: Measures leverage based on market value - Book Leverage: Measures leverage based on book value - Debt-to-Asset Ratio: Captures the proportion of debt in total assets[15] --- Factor Backtesting Results 1. Momentum Factors - **120-Day Momentum**: Weekly return -2.37%[28] - **60-Day Momentum**: Weekly return -2.17%[28] - **20-Day Momentum**: Weekly return -1.69%[28] 2. Volatility Factors - **60-Day Volatility**: Weekly return -1.53%[28] - **20-Day Volatility**: Weekly return -0.96%[28] - **120-Day Volatility**: Weekly return 0.78%[28] 3. Median Deviation - **Weekly Return**: -0.40%[28]

- The report tracks style factors including profitability, volatility, and momentum, which showed strong long positions, while nonlinear market capitalization, valuation, and leverage factors demonstrated strong short positions[3][16] - Barra style factors include Beta (historical beta), market capitalization (logarithm of total market capitalization), momentum (mean of historical excess return series), volatility (weighted combination of historical excess return volatility, cumulative excess return deviation, and residual return volatility), nonlinear market capitalization (third power of market capitalization style), valuation (inverse of price-to-book ratio), liquidity (weighted turnover rates across monthly, quarterly, and yearly periods), profitability (weighted combination of analyst forecast earnings-price ratio, inverse cash flow ratio, and inverse trailing twelve-month PE ratio), growth (weighted combination of earnings growth rate and revenue growth rate), and leverage (weighted combination of market leverage, book leverage, and debt-to-asset ratio)[15] - GRU factors demonstrated strong multi-directional performance across various stock pools, with models like barra5d showing particularly strong positive returns[4][5][7] - GRU long-only portfolio outperformed the CSI 1000 index with excess returns ranging from 0.06% to 0.95% this week, while the barra5d model achieved a year-to-date excess return of 7.75%[8][30][31]

Report Investment Rating - No information available Core Viewpoints - The proportion of short positions in commodities has slightly increased, with differentiation in the precious metals sector and a slight rebound in the agricultural products sector. Currently, the relatively strong sectors are agricultural products and precious metals, while the relatively weak one is energy and chemicals [2]. - In terms of strategy net worth, different factors showed varying trends last week, and the comprehensive signals for different commodities this week are either long, short, or neutral [4][7]. Summaries by Relevant Content Commodity Market Conditions - Precious metals: Gold's time - series momentum declined, while the marginal position of Shanghai silver increased, and short - cycle momentum significantly recovered [2]. - Non - ferrous metals: There were some differences in positions, and the cross - sectional differentiation narrowed, with copper remaining relatively strong [2]. - Black metals: The term structure differentiation narrowed, the position factors of iron ore and rebar increased, and short - cycle momentum factors rose [2]. - Energy and chemicals: The overall short - cycle momentum declined [2]. - Agricultural products: The positions of oilseeds and meals slightly increased, and palm oil remained relatively strong in the term structure [2]. Factor Returns | Factor | Last Week's Return (%) | Current Month's Return (%) | | --- | --- | --- | | Supply | 0.55 (Methanol), - 0.23 (Float glass), - 0.07 (Iron ore), - 0.07 (Aluminum) | 0.00 (Float glass), 0.42 (Iron ore), - 0.19 (Aluminum) | | Demand | 0.00 (Methanol), 0.00 (Float glass), 0.00 (Iron ore), 0.00 (Aluminum) | 0.54 (Methanol), 0.00 (Float glass), - 0.45 (Aluminum) | | Inventory | - 0.19 (Methanol), 0.82 (Float glass), 0.00 (Iron ore), 0.12 (Aluminum) | 0.99 (Methanol), 0.91 (Float glass), - 0.44 (Aluminum) | | Spread | 0.41 (Methanol), 1.11 (Float glass), 0.28 (Iron ore), - 0.28 (Aluminum) | 0.41 (Methanol), 0.28 (Iron ore), - 0.75 (Aluminum) | | Synthetic Factor | 0.43 (Methanol), 0.63 (Float glass), 0.09 (Iron ore), - 0.07 (Aluminum) | 0.27 (Methanol), 0.70 (Float glass), 0.09 (Iron ore), - 0.47 (Aluminum) | [3][4][7] Momentum and Structure Data of Different Sectors | Sector | Momentum Time - series | Momentum Cross - section | Term Structure | Position | | --- | --- | --- | --- | --- | | Black Metals | | 0.09 | 0 | - 0.08 | | Non - ferrous Metals | 0.05 | - 0.21 | 0.52 | 1.13 | | Energy and Chemicals | - 0.02 | 0.18 | 0.37 | 0.69 | | Agricultural Products | 0.13 | 0.35 | 0.41 | - 0.19 | | Stock Index | - 0.71 | 0.46 | - 0.63 | 1.06 | | Precious Metals | 0.12 | | | 0.88 | [5] Fundamental Factors of Different Commodities - **Methanol**: The domestic device capacity utilization rate increased, the supply - side long - position intensity weakened to neutral; traditional downstream manufacturers' raw material procurement decreased, the demand side was neutral to bearish; inland and port inventories continued to increase, the inventory side was bearish; the market price in East and South China coastal areas released a long - position signal, and the spread side was neutral to bullish [4]. - **Float glass**: The enterprise start - up load decreased slightly, the supply side remained neutral; second - tier city commercial housing transaction data released a long - position signal but with weakened intensity, the demand side was neutral to bullish; the inventory of Shanxi enterprises decreased, the inventory side was bullish; the Shenyang - Shahe regional spread factor released a long - position signal, and the spread side was neutral to bullish [7]. - **Iron ore**: The cumulative amount of raw ore continued to decline, the supply - side signal turned neutral; the monthly output of WSA blast furnace pig iron in China continued to decline, the demand - side signal turned neutral; the inventory of 45 ports of iron ore concentrate continued to decline, the inventory side remained neutral; the freight rate of Brazilian Tubarao to Qingdao continued to decline, the spread - side signal remained neutral [7]. - **Aluminum**: SMM domestic lead concentrate processing fees continued to decline, the supply - side signal remained bearish; China's lead alloy exports in May continued to decrease compared to April, the demand - side signal remained neutral; SMM aluminum concentrate monthly balance continued to decline, the inventory side turned neutral; the 0 - 1 spread declined, the spread - side signal remained bearish [7].

Report Summary 1. Report Industry Investment Rating No information about the industry investment rating is provided in the report. 2. Core View of the Report The report presents the market conditions of treasury bond futures on May 27, 2025, including price changes, trading volume, and related factors, and also mentions the situation of the equity market, money market, and macro - industry news, indicating that the expectations for treasury bond futures are limited and the market is in a state of waiting for a direction [1]. 3. Summary by Related Catalogs 3.1 Treasury Bond Futures Market Conditions - On May 27, treasury bond futures closed down across the board, with the 30 - year, 10 - year, 5 - year, and 2 - year main contracts down 0.26%, 0.11%, 0.03%, and 0.02% respectively [1]. - The treasury bond futures index was - 0.12. The volume - price factor was bullish, and the fundamental factor was bearish. Without leverage, the cumulative returns of the strategy in the past 20, 60, 120, and 240 days were 0.04%, - 0.53%, 0.14%, and 1.27% respectively [1]. - The trading volume of the 2 - year, 5 - year, 10 - year, and 30 - year main contracts was 32,028, 43,924, 58,575, and 62,401 respectively, and the open interest was 104,798, 128,934, 165,848, and 92,091 respectively [3]. - The IRR of the 2 - year, 5 - year, 10 - year, and 30 - year active CTD bonds was 1.95%, 2.07%, 1.88%, and 3.58% respectively, and the current R007 was about 1.6794% [3]. 3.2 Equity Market Conditions - On May 27, the equity market oscillated and adjusted throughout the day, with the ChiNext Index leading the decline. The Shanghai Composite Index fell 0.18%, the Shenzhen Component Index fell 0.61%, and the ChiNext Index fell 0.68%. The market hotspots were scattered, and the number of rising and falling stocks was basically the same [1]. 3.3 Money Market Conditions - On May 27, the overnight shibor was 1.4520%, down 5.4bp from the previous trading day; the 7 - day shibor was 1.5980%, up 1.9bp; the 14 - day shibor was 1.6670%, down 2.1bp; the 1 - month shibor was 1.6140%, up 0.2bp [2]. - The bank - to - bank pledged repurchase market traded 2.4 billion yuan, an increase of 1.62%. The overnight rate closed at 1.45%, up 1bp from the previous trading day; the 7 - day rate closed at 1.70%, up 19bp; the 14 - day rate closed at 1.65%, down 4bp; the 1 - month rate closed at 1.60%, down 6bp [4]. 3.4 Bond Yield Curve Conditions - The treasury bond yield curve rose by 0.29 - 1.10BP (the 2 - year yield rose 0.29BP to 1.47%; the 5 - year yield rose 0.78BP to 1.57%; the 10 - year yield rose 0.38BP to 1.72%; the 30 - year yield rose 1.10BP to 1.90%). The credit bond yield curve showed mixed changes [4]. 3.5 Net Long Position Changes by Institution Type - The daily net long position of private funds decreased by 3.27%, foreign capital decreased by 2.46%, and wealth management subsidiaries decreased by 2.4%. The weekly net long position of private funds decreased by 5.28%, foreign capital decreased by 4.11%, and wealth management subsidiaries decreased by 3.69% [6]. 3.6 Macro and Industry News - On May 27, the central bank conducted 448 billion yuan of 7 - day reverse repurchase operations at an operating rate of 1.40%, unchanged from before. There were 357 billion yuan of reverse repurchases due on the same day [8]. 3.7 Trend Intensity - The trend intensity of treasury bond futures was 0, indicating a neutral state [9].

Group 1: ETF Rotation Strategy Performance - The ETF rotation strategy, constructed using GBDT+NN machine learning factors, has shown excellent out-of-sample performance with an IC value of 44.48% and a long position excess return of 0.73% last week [3][14] - The annualized excess return of the strategy is 11.88%, with a maximum drawdown of 17.31% [17][18] - Recent performance includes an excess return of 0.20% last week, 1.64% for the month, and 0.35% year-to-date [18][20] Group 2: High-Frequency Factor Overview - Various high-frequency factors have demonstrated strong overall performance, with the price range factor showing a long position excess return of 4.93% year-to-date, while the regret avoidance factor has underperformed with a return of 0.27% [4][22] - The price range factor measures the activity level of stocks within different price ranges, indicating investor expectations for future price movements [5][25] - The regret avoidance factor reflects the impact of investor emotions on stock price expectations, showing stable out-of-sample excess returns [5][37] Group 3: High-Frequency and Fundamental Factor Combination - A combined strategy of high-frequency and fundamental factors has been developed, yielding an annualized excess return of 14.76% with a maximum drawdown of 4.52% [6][59] - The strategy has shown stable out-of-sample performance, with a year-to-date excess return of 3.74% [60] - The integration of fundamental factors with high-frequency factors has improved the performance metrics of the strategy [57][59]

证券研究报告：金融工程报告 研究所 - 2025.04.14 金工周报 高波强势，基本面回撤——中邮因子周报 20250504 分析师:肖承志 SAC 登记编号:S1340524090001 Email:xiaochengzhi@cnpsec.com 研究助理:金晓杰 SAC 登记编号:S1340124100010 Email:jinxiaojie@cnpsec.com 近期研究报告 《基金 Q1 加仓有色汽车传媒，减仓电 新食饮通信——公募基金 2025Q1 季报 点评》 - 2025.04.30 《年报效应边际递减，右侧买入信号 触发——微盘股指数周报 20250427》 - 2025.04.27 《动量波动分化，低波高涨占优—— 中邮因子周报 20250427》 - 2025.04.27 《OpenAI 发布 GPT-4.1，智谱发布 GLM-4-32B-0414 系列——AI 动态汇总 20250421》 - 2025.04.23 《国家队交易特征显著，短期指数仍 交易补缺预期，TMT 类题材仍需等待— —行业轮动周报 20250420》 - 2025.04.21 《小市值强势，动量风格占优——中 邮 ...

证券研究报告：金融工程报告 研究所 分析师:肖承志 SAC 登记编号:S1340524090001 Email:xiaochengzhi@cnpsec.com 研究助理：金晓杰 SAC 登记编号:S1340124100010 Email:jinxiaojie@cnpsec.com 近期研究报告 小市值强势，动量风格占优——中邮因子周报 20250420 l 风格因子跟踪 本周估值、杠杆、动量因子的多空表现强势，市值、非线性市值、 流动性因子的空头表现较强。 《Meta LIama 4 开源，OpenAI 启动先 锋计划——AI 动态汇总 20250414》 - 2025.04.15 《小市值持续，高低波风格交替—— 中邮因子周报 20250413》 - 2025.04.14 《4 月是否还会有"最后一跌"？ ——微盘股指数周报 20250406》 - 2025.04.07 《"924"以来融资资金防守后均见到 行情低点，仍关注科技配置机会—— 行业轮动周报 20250330》 - 2025.03.31 《英伟达召开 GTC 2025 大会， Skywork-R1V、混元 T1 等推理模型接 连上线——AI 动 ...

Group 1: ETF Rotation Strategy Tracking - The ETF rotation strategy, constructed using GBDT+NN machine learning factors, has shown strong performance in out-of-sample testing, with an annualized excess return of 11.90% and a maximum drawdown of 17.31% [2][12][17] - Recent performance indicates a weekly excess return of 0.77% and a monthly excess return of 1.10%, while the year-to-date excess return stands at -0.19% [20][24] - The strategy's information ratio is 0.68, reflecting its effectiveness in generating excess returns relative to risk [24] Group 2: High-Frequency Factor Overview - High-frequency factors have demonstrated overall strong performance, with the price range factor yielding a year-to-date excess return of 4.79% and the price-volume divergence factor achieving 10.08% [3][20] - The regret avoidance factor has underperformed with a year-to-date excess return of -0.56%, while the slope convexity factor has shown a year-to-date excess return of -3.64% [3][20] - The high-frequency "gold" combination strategy has an annualized excess return of 10.69% and a maximum drawdown of 6.04% [5][60] Group 3: High-Frequency Factor Performance Tracking - The price range factor measures the activity level of stocks within different price ranges, showing strong predictive power and stable performance this year [4][28] - The price-volume divergence factor assesses the correlation between stock price and trading volume, with recent performance indicating a mixed stability [4][39] - The regret avoidance factor reflects investor behavior, showing stable out-of-sample excess returns, while the slope convexity factor illustrates the impact of order book elasticity on expected returns [4][51] Group 4: Combined Strategies Performance - The high-frequency and fundamental resonance combination strategy has an annualized excess return of 14.98% and a maximum drawdown of 4.52% [5][64] - Recent performance for this combined strategy includes a weekly excess return of 0.63% and a monthly excess return of 2.00%, with a year-to-date excess return of 4.69% [67]