Report Industry Investment Rating No relevant information provided. Core Viewpoints of the Report - T0 strategies, with low risk exposure and high return - drawdown ratios, are attracting more attention. Stock T0 strategies have an annualized return of 5% - 20% and a drawdown of around 1%, making them popular as alternative absolute - return strategies. Futures T0 strategies are more advantageous carriers, offering high liquidity, low costs, and leverage, and having lower slippage compared to commodity futures [1]. - Combining deep - learning - based medium - low - frequency momentum/reversal strategies is a viable approach for futures T0 strategies. The K - Shape algorithm is used to classify intraday trends into three types: upward, downward, and sideways. An MLP + GRU neural network is used to predict these trends, with a validation set win - rate increasing from 33% to 40%. By integrating these predictions with an intraday CTA base strategy, the strategy can achieve a post - fee annualized return of 11.19% and a drawdown of 3.62%, and over 30% annualized return on the IM contract [2][3][4]. Summary According to the Table of Contents 1. Analysis of the Characteristics of Futures T0 Strategies 1.1 From Stock T0 to Futures T0 Strategies - **Stock T0 Strategies**: T0 strategies are less affected by index trends and macro - economic conditions, and more related to turnover and intraday amplitude. They can be divided into manual and programmed T0. Their annualized returns range from 5% to 20%, with small drawdowns, and are suitable for small - scale funds or large - position strategies. There are already mature third - party algorithm providers collaborating with brokerages [9][12][13]. - **Advantages of Futures T0 Strategies**: Futures offer a T + 0 trading mechanism, high liquidity, sufficient amplitude, low trading costs, and leverage. They also have lower slippage compared to commodity futures, providing a better platform for T0 strategies [16][18]. - **Significance for Multi - asset and Multi - strategy Allocation**: Futures T0 strategies can diversify asset allocation, provide free leverage and short - side returns, and improve the performance of traditional asset portfolios. For example, adding a CTA - like strategy to a basic asset pool can increase the annualized return of a risk - parity strategy from 5.50% to 6.67% and reduce the maximum drawdown from 6.71% to 3.74% [19][21]. 1.2 Exploration of Futures T0 Strategy Paradigms - **Differences from Traditional Strategies**: T0 strategies have time - limited opening and closing positions, a narrowing decision - making space, and are highly susceptible to high - frequency information flows, requiring strict trading discipline [23]. - **Specific Implementation Logics**: - **Micro - structure Strategies Based on Order Books**: Analyze high - frequency data such as order book volume and price distribution to predict short - term price trends, with high trading frequencies [25]. - **Momentum/Reversal and Statistical Arbitrage Strategies**: Based on financial time - series statistical laws, with medium - low trading frequencies. Momentum strategies follow trends, while reversal strategies capture corrective rebounds [26]. - **Combination of Machine/Deep Learning with Traditional Paradigms**: Machine and deep learning can automatically learn complex non - linear patterns from large - scale, high - dimensional, and noisy data, and are used in the above two types of strategies [27]. 2. T0 Framework Based on Intraday Trend Pattern Prediction 2.1 Review of Time - Series Clustering Algorithms - **DTW + K - Means**: DTW can measure the similarity between time series, overcoming translation, scaling, and periodic invariance. Combined with K - Means, it can cluster intraday index trends, but is affected by outliers and has high computational complexity [33][39][40]. - **K - Shape**: A time - series clustering algorithm using shape - based distance (SBD) to measure similarity, with translation and scaling invariance. It has better computational efficiency and cluster - center representation, and is used for subsequent analysis [41]. 2.2 Clustering Performance of the K - Shape Algorithm on Stock Index Spot - The K - Shape algorithm is used to cluster the intraday trends of the Shanghai 50, CSI 300, CSI 500, and CSI 1000. Initially, 20 - category clustering is performed, and then reduced to 8 categories. The cluster centers are explicitly initialized, and the final three - category classification (upward, downward, and sideways) is used for subsequent prediction [48][51][53]. 2.3 Prediction of Trend Pattern Labels Based on Deep Learning - For medium - low - frequency T0 strategies, predicting trend types is more meaningful than predicting returns. An MLP neural network with a Softmax output layer is used, integrating cross - sectional and time - series price - volume features. The validation set win - rate can increase from 12.5% to 20.35%, and for the three - category classification, it can increase from 33% to 40%. The model is retrained quarterly to ensure stable performance [57][58][65]. 2.4 T0 Baseline Strategy: Intraday ATR Breakout - The intraday ATR breakout strategy is a trend - following strategy that uses the previous day's ATR to set trading intervals, with opening, stop - profit, and stop - loss thresholds. It is sensitive to trading fees. Under a unilateral fee rate of 0.0025%, the CSI 300, CSI 500, and CSI 1000 can achieve positive long - term returns [72][75][80]. 2.5 Futures T0 Strategy Based on Trend Pattern Prediction - By predicting intraday trends, the application and parameters of the base strategy can be adjusted. For example, on four equal - weighted contracts from January 2023 to June 2025, the annualized return can increase from 6.65% to 11.19%, and the maximum drawdown can be reduced from 7.45% to 3.62% [84][86][87]. 2.6 Summary and Outlook - Futures T0 strategies are more advantageous than stock T0 strategies, and an intraday trend pattern prediction + intraday CTA framework is used to construct the strategy. Future research can focus on improving trend prediction by adding more information and developing reversal CTA strategies [92][93][96].

证券研究报告 | 金融工程 gszqdatemark 2025 10 12 年 月 日 风格上，当前价值因子占优。从纯因子收益来看，本周有色金属、钢铁、 国防军工等行业因子相对市场市值加权组合跑出较高超额收益，消费 者服务、银行等行业因子回撤较多；风格因子中，价值因子超额收益较 高，Beta、残差波动率呈较为显著的负向超额收益。从近期因子表现来 看，高杠杆、高成长股表现优异，残差波动率、价值等因子表现不佳。 风险提示：量化周报观点全部基于历史统计与量化模型，存在历史规律与 量化模型失效的风险。 作者 分析师 刘富兵 执业证书编号：S0680518030007 邮箱：liufubing@gszq.com 分析师 林志朋 执业证书编号：S0680518100004 邮箱：linzhipeng@gszq.com 分析师 沈芷琦 执业证书编号：S0680521120005 邮箱：shenzhiqi@gszq.com 分析师 梁思涵 执业证书编号：S0680522070006 邮箱：liangsihan@gszq.com 分析师 张国安 执业证书编号：S0680524060003 量化周报 创业板、科创 50 短期内或 ...

Core Insights - In September, A-shares indices reached new highs for the year, with the Shanghai Composite Index slightly up by 0.64%, while the Shenzhen Component Index and ChiNext Index rose by 6.54% and 12.04% respectively [2] - Approximately 80.49% of the private equity products under billion-yuan private equity firms achieved historical net value highs in September, with a total of 429 products meeting the criteria of being established for over a year and having performance displayed on the platform [2][3] - Among the products, quantitative strategies accounted for 263, while non-quantitative strategies had 166, with stock strategy products being the most prevalent at 364 [2] Private Equity Performance - Fourteen billion-yuan private equity firms had all their products reach historical highs in September, with eight being quantitative and four subjective, while twelve focused on stock strategies [3] - The top five private equity firms based on average returns over the past year include Lingjun Investment, Fusheng Asset, Kaishi Private Equity, Ningbo Huansheng Quantitative, and Chengqi Asset [4] Notable Firms and Strategies - Lingjun Investment, established in 2014, has a strong research team with over 85% of its members holding master's or doctoral degrees from prestigious universities, focusing on fundamental factor research to enhance strategy resilience [6] - Blackwing Asset, Rido Investment, Dongfang Port, JQK Investment, and Tianyan Capital all had over 90% of their products reach historical highs in September [6] - Dongfang Port, led by Dan Bin, had 74 products reach historical highs, representing 93.67% of its offerings, primarily due to a strong focus on AI-related investments [8] Top Performing Products - The threshold for the top 20 products achieving historical highs in the past year exceeded a certain percentage, with 15 being quantitative long products [9] - The leading product in terms of performance is "Duration Macro Multi-Strategy" from Duration Investment, which has shown significant returns over the past three years and five years [10][12] - Fusheng Asset's "Fusheng Positive Energy No. 2" product is noted for its outstanding performance over five years, with a significant return in the first three quarters of the year [17] Market Outlook - Fusheng Asset expressed optimism about the overall market performance, indicating a gradual economic recovery and a shift in market dynamics [17]

Core Viewpoint - The issuance of new funds has surged post the National Day holiday, with a total of 51 new funds launched during the week from October 13 to October 17, indicating a strong recovery in the fund issuance market, particularly in equity funds [2][6]. Fund Issuance Overview - A significant portion of the new funds, 31 out of 51, were launched on Monday, October 13, accounting for 60.78% of the total new funds for the week [4]. - The average subscription period for the new funds was 12.59 days, which is a noticeable decrease compared to previous periods [5]. - The longest subscription period was 21 days for the 华夏上证 180ETF 联接, while the shortest was just 2 days for two public REITs products [6]. Fund Types and Composition - Equity funds dominated the new fund landscape, with 42 out of 51 funds classified as equity funds, representing 82.35% of the total [7]. - Among the equity funds, 28 were index equity funds, making up 66.67% of the equity category [8]. - The new funds included a variety of themes, such as those tracking Hong Kong Stock Connect indices and those focused on the STAR Market and ChiNext indices [8]. Active Equity Funds - There were 14 actively managed equity funds launched, including 11 mixed funds and 3 ordinary stock funds, reflecting a diverse investment strategy among fund companies [9]. - The active equity funds featured several quantitative theme products and a range of investment styles, from technology growth to balanced value strategies [9]. Bond Funds and Market Trends - Only 3 bond funds were launched during the week, indicating a decline in interest in bond funds as equity markets show signs of recovery [9]. - The "fixed income plus" funds have gained attention, suggesting a shift in investor preference towards more flexible investment strategies [9]. - The overall sentiment in the fund issuance market is improving, with expectations for continued growth in equity fund issuance if market conditions remain favorable [9].

金融工程| 证券研究报告 —周报 2025 年 10 月 13 日 中银量化大类资产跟踪 市场整体回撤，红利指数大幅跑赢创业板指 股票市场概览 本周 A 股下跌，港股下跌，美股下跌，其他海外权益市场普遍上涨。 A 股风格与拥挤度 成长 vs 红利：成长风格拥挤度及超额净值持续处于历史低位；红利 风格拥挤度近期处于历史较低位置。 小盘 vs 大盘：小盘风格拥挤度近期上升至历史均衡位置，大盘风格 拥挤度近期上升至历史高位。 微盘股 vs 基金重仓：微盘股拥挤度下降至历史低位；基金重仓超额 累计净值持续处于历史低位，拥挤度近期上行至历史高位。 A 股行情及成交热度 本周领涨的行业为有色金属、煤炭、钢铁；领跌的行业为传媒、消费者 服务、电子。本周成交热度最高的行业为国防军工、有色金属、机械； 成交热度最低的行业为农林牧渔、综合金融、食品饮料。 A 股估值与股债性价比 A 股资金面 机构调研活跃度 当前机构调研活跃度历史分位居前的行业为有色金属、钢铁、交通运 输，居后的行业为医药、银行、机械。 利率市场 本周中国国债利率下跌，美国国债利率下跌，中美利差处于历史高位。 汇率市场 近一周在岸人民币较美元贬值，离岸人民币较美 ...

Investment Rating - The report indicates a cautious outlook on the market, highlighting high volatility and potential risks that could disrupt current optimism [1][3]. Core Insights - The S&P index has declined approximately 1.25%, with CTA no longer acting as buyers, indicating heightened market risk [1][3]. - The non-profitable tech sector has seen a parabolic rise driven by retail investors and a $100 billion digital impact, suggesting signs of market exuberance [1][5]. - Emerging market stocks have performed well over the past six months, reflecting diversified growth across the region rather than being solely driven by China [1][11]. Summary by Sections Market Performance - The implied volatility remains high despite a rising stock market, as investors continue to buy put options [4]. - Quality stocks have outperformed the S&P 500 index, with a basket of short-term stocks exceeding the index by approximately 100 basis points on a given day [4]. Sector Analysis - The non-profitable tech sector's recent surge is attributed to active retail investors and discussions around significant digital investments [5]. - AI-related trades are gaining attention, with concerns about private credit risks permeating various sectors [5]. Gold Market - Gold prices have surpassed $4,000, reflecting themes of inflation and government spending, establishing itself as a de facto safe-haven asset [8]. - Central bank demand is driving gold prices, indicating a non-speculative boom in the market [8]. Emerging Markets - Emerging market stocks have shown strong performance, with 70% of the broad index maintaining positive monthly returns throughout the year [11]. - The performance is not solely led by China but includes significant contributions from regions like Europe, the Middle East, and Latin America [11]. AI Development - AI technology is penetrating emerging market companies, particularly in China and North Asia, although their investment portfolios lag behind U.S. counterparts [14]. - The current state of AI in emerging markets is still in early development, with a notably lower allocation in global funds compared to benchmarks [14].

Core Insights - The article highlights the rapid advancement of AI in quantitative investment, with Minsheng Jianyin Fund as a pioneer in this "AI race" [1] - The firm has developed a "data-feature-strategy-portfolio" closed-loop system over four years, creating a unique competitive advantage in AI-driven quantitative investment [1][6] Group 1: AI Quantitative Investment Strategy - Minsheng Jianyin's AI quantitative strategy integrates market perception, engineering capabilities, and advanced algorithm applications [1] - The transition from traditional quantitative models to AI models allows for the capture of complex non-linear market relationships, enhancing predictive accuracy [5][7] - The firm emphasizes the necessity of AI in the survival of public funds, predicting a future ecosystem dominated by "AI-led quantification and tool-based index products" [10] Group 2: Market Opportunities and Performance - The National Securities 2000 Index is viewed as a valuable asset for technology upgrades and quantitative enhancement, with significant structural opportunities in AI and high-end manufacturing [2][8] - The Minsheng Jianyin National Securities 2000 Index Enhanced Fund has outperformed its benchmark, achieving returns of 17.18% and 49.66% over six months and one year, respectively [8] - The index's diverse composition and low pricing efficiency provide fertile ground for capturing alpha through quantitative strategies [8] Group 3: Challenges and Risk Management - AI models are not infallible; they rely on historical data and may face challenges during extreme market conditions, highlighting the importance of risk management [9] - The firm maintains that AI enhances human cognitive boundaries rather than replacing human judgment, allowing for the analysis of complex relationships among thousands of stocks [9]

本文首发于公众号"私募排排网"。 （点击↑↑ 上图查看详情 ） 上海佳期私募基金管理有限公司（以下简称"佳期投资"）自2014年成立以来，始终以科学、系统化的投资理念为指引，依托持续的技术创新，在充满 变数的资本市场中不断前行，致力于在严控风险的基础上为客户创造可持续的优质回报。目前，佳期投资的管理规模约400亿元。 精英汇聚，夯实人才基石 佳期投资团队是国内专注于量化投资的早期实践者。 历经十余年市场周期淬炼，团队在跨资产类别投资中积累了深厚的实战经验。目前公司团 队规模超过150人，近80%成员拥有硕士或博士学历，背景高度集中于数学、物理、统计学、计算机科学等STEM领域，主要毕业于清华、北 大、复旦、上海交大、中科大，以及哈佛、普林斯顿、斯坦福、耶鲁等海内外顶尖高校。 团队成员中不乏曾在国际权威期刊发表论文、斩获知名学术竞赛奖项的科研人才，亦有多人具备国内外顶尖金融机构或科技企业的资深从业经 验。这一高度 专业化、多元化的"全明星"阵容 ，为公司持续发展构筑了坚实的人才基础和核心竞争力。 创新驱动，构筑硬核实力 佳期投资始终将科技创新视为发展驱动力，不仅在研发算力设施上持续重投入，更在多个创新性研发方向 ...

Core Insights - The divergence in opinions among Federal Reserve officials reflects varying interpretations of economic conditions and highlights the differences in information processing capabilities among different investor groups [1][3][6] Group 1: Market Reactions to Policy Changes - Significant market movements often precede public announcements, indicating that institutional investors act on information before it reaches retail investors [3][6] - The phenomenon known as "information ladder effect" suggests that institutional investors are always a few steps ahead of retail investors, utilizing various methods to capture underlying market trends [6][8] Group 2: Investment Strategies and Data Analysis - The nature of capital flows is crucial in understanding market reactions; not all positive news leads to positive stock performance, as some rebounds may be driven by speculative trading while others indicate institutional accumulation [8] - The increasing complexity of the market, with over 30% of trading being algorithmic, emphasizes the importance of analyzing trading behavior data to understand true market dynamics [8][9] Group 3: Focus on Capital Flows - Attention should be directed towards how different asset classes respond to varying economic conditions, particularly in scenarios of moderate growth and controlled inflation [8] - The ability to filter out noise and focus on data-driven insights is essential for making informed investment decisions in an information-saturated environment [8]

Core Insights - The precious metals market is experiencing significant growth, with gold surpassing $4000 and silver increasing by 75% year-to-date, attracting many investors [1] - Despite the bullish market, retail investors often face higher probabilities of losses during such rallies due to a lack of understanding of market dynamics [3] Market Dynamics - Factors such as rising expectations for Federal Reserve interest rate cuts and geopolitical uncertainties are driving gold prices upward [3] - The importance of understanding macroeconomic factors and translating them into actionable strategies is emphasized for ordinary investors [3] Investor Behavior - Many investors tend to overestimate their judgment during price increases and doubt their decisions during price declines, illustrating the "hindsight bias" phenomenon [4] - Historical examples show that even during significant price rallies, few investors manage to retain their profits due to premature exits or panic selling [4] Quantitative Investment Concepts - The concepts of "empty rise" and "virtual drop" are introduced, where "empty rise" refers to price increases without substantial support, and "virtual drop" indicates price declines despite strong fundamentals [5] - The analysis of institutional trading behavior is crucial for distinguishing between these two phenomena, as market pricing power lies with institutional investors [7] Institutional Indicators - The "institutional inventory" metric is highlighted as a key indicator of institutional trading activity, with higher levels indicating active participation [9] - Continuous institutional activity can provide reassurance during price corrections, suggesting that such moments may represent buying opportunities [9] Future Projections - Predictions from UBS and Mingming suggest potential future gold prices of $4200 and $4500 per ounce, respectively, but the focus should remain on institutional movements rather than speculative top guessing [13] - Data from the World Gold Council indicates that central bank gold purchases are expected to reach 415 tons in the first half of 2025, providing a solid foundation for gold prices [13] Silver Market Insights - The silver market is characterized by increased investment demand and low supply elasticity, with significant increases in holdings in the largest silver ETF [13] Strategic Recommendations - Investors are advised to avoid being misled by short-term fluctuations and to focus on concrete data indicators for decision-making [14] - Distinguishing between "empty rises" and "virtual drops" is essential, with the latter presenting potential buying opportunities [14] - Utilizing quantitative tools like "institutional inventory" can help investors understand market fundamentals and avoid emotional trading [15]