Quantitative Models and Construction Methods 1. Model Name: A-Share Technical Scoring Model - **Model Construction Idea**: The model aims to fully explore technical information to depict market conditions, breaking down the abstract concept of "market state" into five dimensions: price, volume, volatility, trend, and crowding. It generates a comprehensive score ranging from -1 to +1 based on equal-weighted voting of signals from 10 selected indicators across these dimensions[9][14] - **Model Construction Process**: 1. Select 10 effective market observation indicators across the five dimensions[14] 2. Generate long/short timing signals for each indicator individually 3. Aggregate the signals through equal-weighted voting to form a comprehensive score between -1 and +1[9] - **Model Evaluation**: The model provides a straightforward and timely way for investors to observe and understand the market[9] 2. Model Name: Style Timing Model (Small-Cap Crowding) - **Model Construction Idea**: The model uses a crowding-based trend approach to time large-cap and small-cap styles. Crowding is measured by the difference in momentum and trading volume ratios between small-cap and large-cap indices[3][20] - **Model Construction Process**: 1. Calculate the momentum difference between the Wind Micro-Cap Index and the CSI 300 Index across 10/20/30/40/50/60-day windows 2. Compute the trading volume ratio between the two indices over the same windows 3. Derive crowding scores for small-cap and large-cap styles by averaging the highest and lowest quantiles of the above metrics, respectively 4. Combine the momentum and volume scores to obtain the final crowding score. A score above 90% indicates high small-cap crowding, while below 10% indicates high large-cap crowding[25] - **Model Evaluation**: The model effectively captures the dynamics of style crowding and provides actionable insights for timing decisions[20][25] 3. Model Name: Industry Rotation Model (Genetic Programming) - **Model Construction Idea**: The model applies genetic programming to directly extract factors from industry indices' price, volume, and valuation data, without relying on predefined scoring rules. It uses a dual-objective approach to optimize factor monotonicity and top-group performance[28][32][33] - **Model Construction Process**: 1. Use NSGA-II algorithm to optimize two objectives: |IC| (information coefficient) and NDCG@5 (normalized discounted cumulative gain for top 5 groups) 2. Combine weakly collinear factors using a greedy strategy and variance inflation factor to form industry scores 3. Select the top 5 industries with the highest multi-factor scores for equal-weight allocation, rebalancing weekly[32][34] - **Model Evaluation**: The dual-objective genetic programming approach enhances factor diversity and reduces overfitting risks, making it a robust tool for industry rotation[32][34] 4. Model Name: China Domestic All-Weather Enhanced Portfolio - **Model Construction Idea**: The model adopts a macro-factor risk parity framework, emphasizing risk diversification across underlying macro risk sources rather than asset classes. It actively overweights favorable quadrants based on macro momentum[39][42] - **Model Construction Process**: 1. Divide macro risks into four quadrants based on growth and inflation expectations: growth above/below expectations and inflation above/below expectations 2. Construct sub-portfolios within each quadrant using equal-weighted assets, focusing on downside risk 3. Adjust quadrant risk budgets monthly based on macro momentum indicators, which combine buy-side momentum from asset prices and sell-side momentum from economic forecast surprises[42] - **Model Evaluation**: The strategy effectively integrates macroeconomic insights into portfolio construction, achieving enhanced performance through active allocation adjustments[39][42] --- Model Backtesting Results 1. A-Share Technical Scoring Model - Annualized Return: 20.78% - Annualized Volatility: 17.32% - Maximum Drawdown: -23.74% - Sharpe Ratio: 1.20 - Calmar Ratio: 0.88[15] 2. Style Timing Model (Small-Cap Crowding) - Annualized Return: 28.46% - Maximum Drawdown: -32.05% - Sharpe Ratio: 1.19 - Calmar Ratio: 0.89 - YTD Return: 11.85% - Weekly Return: 5.25%[26] 3. Industry Rotation Model (Genetic Programming) - Annualized Return: 32.92% - Annualized Volatility: 17.43% - Maximum Drawdown: -19.63% - Sharpe Ratio: 1.89 - Calmar Ratio: 1.68 - YTD Return: 6.80% - Weekly Return: 3.37%[31] 4. China Domestic All-Weather Enhanced Portfolio - Annualized Return: 11.93% - Annualized Volatility: 6.20% - Maximum Drawdown: -6.30% - Sharpe Ratio: 1.92 - Calmar Ratio: 1.89 - YTD Return: 3.59% - Weekly Return: 1.54%[43] --- Quantitative Factors and Construction Methods 1. Factor Name: Small-Cap Crowding Factor - **Factor Construction Idea**: Measures the crowding level of small-cap style based on momentum and trading volume differences between small-cap and large-cap indices[20][25] - **Factor Construction Process**: 1. Calculate momentum differences and trading volume ratios for multiple time windows 2. Derive crowding scores by averaging the highest and lowest quantiles of these metrics 3. Combine momentum and volume scores to obtain the final crowding score[25] 2. Factor Name: Industry Rotation Factor (Genetic Programming) - **Factor Construction Idea**: Extracts factors from industry indices using genetic programming, optimizing for monotonicity and top-group performance[32][34] - **Factor Construction Process**: 1. Perform cross-sectional regression of standardized daily trading volume against daily price gaps to obtain residuals (Variable A) 2. Identify the trading day with the highest standardized volume in the past 9 days (Variable B) 3. Conduct time-series regression of Variables A and B over the past 50 days to obtain intercepts (Variable C) 4. Compute the covariance of Variable C and standardized monthly opening prices over the past 45 days[38] --- Factor Backtesting Results 1. Small-Cap Crowding Factor - YTD Return: 11.85% - Weekly Return: 5.25%[26] 2. Industry Rotation Factor (Genetic Programming) - Training Set IC: 0.340 - Factor Weight: 18.7% - YTD Return: 6.80% - Weekly Return: 3.37%[31][38]

港股财务数据处理六问及因子复现手册 glmszqdatemark 2026 年 01 月 25 日 [Table_Author] | 分析师 | 叶尔乐 | | --- | --- | | 执业证书： S0590525110059 | | | 邮箱： | yeerle@glms.com.cn | | 研究助理 | 裴钰琪 | | 执业证书： S0590125110081 | | | 邮箱： | peiyuqi@glms.com.cn | 量化专题报告 相关研究 本公司具备证券投资咨询业务资格，请务必阅读最后一页免责声明 证券研究报告 1 港股与 A 股市场特征存在显著差异，直接影响因子有效性逻辑。本报告聚焦港股 因子投资体系，构建并测试基本面与价量两类核心因子，同时解决财务数据处理 关键问题。港股以机构投资者为主，实行 T+0 交易且无涨跌幅限制，低估值、高 股息标的更受青睐，而 A 股个人投资者占比高，成长股估值弹性更强。报告选取 港股通与全港股（剔除仙股）两个股票池，采用月频调仓、市值行业中性化处理， 回测区间分别为 2014 年 11 月至 2025 年 12 月、2012 年 12 月至 2025 年 ...

此次扩容呈现出两个鲜明趋势：一是"多元化"，具有险资背景的百亿私募增至3家，外资百亿私募也增 至2家；二是"量化主导"，在当前118家百亿私募中，量化策略机构多达55家，占比高达46.61%，稳固占 据主流；主观策略私募有48家，占比40.68%，主观与量化混合策略私募有12家，占比10.17%。这从规 模层面印证了，量化投资已成为头部机构不可忽视的核心力量。 MACD金叉信号形成，这些股涨势不错！ 格隆汇1月25日｜据时代财经，一边是争议不断，一边是业绩狂飙，被一些市场人士吐槽在股市"割韭 菜"的量化私募在2025年取得了好成绩：40家百亿量化私募全部正收益，超20家业绩翻倍。近日，私募 排排网统计显示，全年有业绩展示的244家量化私募旗下股票策略产品平均收益达36.72%，其中正收益 机构达239家，占比高达97.95%。 量化私募交出惊人业绩的同时，百亿私募俱乐部也在急速扩容与洗牌。根据最新数据，截至2026年1月 23日，百亿证券私募管理人总数已增至118家，较2025年末净增5家。阵营内部新陈代谢活跃：当月有4 家机构退出，同时有9家机构新晋或重返百亿行列。 ...

Core Viewpoint - The AI Fund Xiangcai New Energy Quantitative Stock Mixed A (020779) reported a profit of 60,900 yuan in Q4 2025, with a net value growth rate of 2.1% for the period, and a total fund size of 7.3649 million yuan by the end of Q4 2025 [2][15]. Fund Performance - As of January 22, the fund's unit net value was 1.431 yuan, with a one-year cumulative net value growth rate of 52.82%, the highest among its peers [2][3]. - The fund's performance over the last three months showed a growth rate of 12.77%, ranking 230 out of 689 comparable funds, and a six-month growth rate of 39.87%, ranking 127 out of 689 [3]. Investment Strategy - The fund management emphasizes a long-term development trend in the new energy sector, utilizing quantitative investment advantages and focusing on high-growth segments such as photovoltaics, wind power, energy storage, and new energy vehicles [3]. - The management plans to continue focusing on the new energy industry, seeking high-quality stocks aligned with technological advancements and industry trends [3]. Risk and Return Metrics - The fund has a Sharpe ratio of 1.313 since inception, indicating a favorable risk-adjusted return [7]. - The maximum drawdown since inception is 16.67%, with the largest quarterly drawdown occurring in Q2 2025 at 10.85% [10]. Portfolio Composition - The average stock position since inception is 75.67%, compared to a peer average of 84.04%, with the highest stock position reaching 83.86% at the end of Q1 2025 [13]. - As of Q4 2025, the top ten holdings include companies such as Hongfa Technology, CATL, and Sungrow Power Supply [18].

- The report highlights the performance of the quantitative stock portfolios, including the CSI 300 enhanced portfolio, which achieved a weekly excess return of 2.16% and a cumulative excess return of 5.70% in 2026[1][15][14] - The CSI 500 enhanced portfolio recorded a weekly excess return of 0.38% and a cumulative excess return of -1.98% in 2026[15][14][17] - The CSI 1000 enhanced portfolio achieved a weekly excess return of 0.96% and a cumulative excess return of 1.56% in 2026[15][14][24] - The PB-Earnings optimized portfolio delivered a weekly excess return of 4.05% and a cumulative excess return of 3.64% in 2026[30][31][32] - The GARP portfolio achieved a weekly excess return of 5.85% and a cumulative excess return of 8.81% in 2026[33][34] - The Small-cap Value Optimized Portfolio 1 recorded a weekly excess return of -0.75% and a cumulative excess return of -1.42% in 2026[35][36] - The Small-cap Value Optimized Portfolio 2 achieved a weekly excess return of 0.70% and a cumulative excess return of 2.23% in 2026[37][38] - The Small-cap Growth Portfolio delivered a weekly excess return of -0.24% and a cumulative excess return of -0.57% in 2026[39][40] - Style factors showed that small-cap stocks outperformed large-cap stocks, and low valuation stocks outperformed high valuation stocks. The market capitalization factor achieved a weekly multi-long-short return of 2.83%, while the PB factor and PE_TTM factor achieved 1.05% and 0.71%, respectively[42][43][45] - Technical factors indicated positive contributions from turnover rate factors, while reversal and volatility factors showed negative returns. The turnover rate factor achieved a weekly multi-long-short return of 0.48%, while reversal and volatility factors recorded -2.05% and -0.98%, respectively[46][48][49] - Fundamental factors demonstrated positive returns from SUE and adjusted net profit expectation factors. The SUE factor achieved a weekly multi-long-short return of 0.82%, while adjusted net profit expectation factors recorded 0.47%. ROE factors showed a negative return of -0.67%[50][51][52]

Core Insights - 2025 is a landmark year for quantitative investment, marked by the emergence of DeepSeek, which injects disruptive AI momentum into the field [3] - The A-share market has shown a significant upward trend, with small and mid-cap stocks outperforming, as evidenced by the over 36% and 80% increases in the CSI 2000 and micro-cap indices respectively [3] - The average return for quantitative private equity products in 2025 reached 30.28%, with a geometric excess return of 10.83% [3] Quantitative Strategy Performance - The top-performing quantitative long strategy products, totaling 806, achieved returns of 44.74% and geometric excess returns of 16.46% in 2025, leading among private equity secondary strategies [4] - Other strategies such as quantitative CTA and stock market neutral also performed well, with average returns of 20.21% and 9.58% respectively [4][5] Quantitative Stock Selection - The average return for quantitative stock selection products was 42.28% in 2025, with an average excess return of 17.70% [6] - The top three products in this category were from Hainan Gaia Qingke Private Equity, Water Mill Asset, and Hanrong Investment [6] Notable Products and Managers - Hainan Gaia Qingke's product "Gaia Qingke Cattail Progress A" achieved outstanding performance, with returns exceeding ***% [7] - Hanrong Investment's "Hanrong Ansheng Progress No. 1 B" also performed well, with returns exceeding ***% [8] - Longqi Technology's "Longqi Technology Innovation Selected No. 1 C" led the quantitative stock selection products with returns exceeding ***% [9] CSI 500 Index Enhancement - The average return for CSI 500 index enhancement products was 46.32% in 2025, with an average excess return of 12.22% [10] - The top three products in this category were from Guobiao Asset, Zhaoxin Private Equity Fund, and Zhaoyue Private Equity [10] CSI 1000 Index Enhancement - The average return for CSI 1000 index enhancement products was 49.68% in 2025, with an average excess return of 17.41% [14] - The top three products were from Jintong Investment, Luxiu Investment, and Mengxi Investment [14] Other Index Enhancements - The average return for other index enhancement products was 46.76% in 2025, with an average excess return of 19.95% [23] - The top three products in this category were from Jing Shang Jia Wan, Zhongmin Huijin, and Yang Shi Asset [24]

Core Insights - The article discusses the development and practices of Ganyue Investment in the quantitative investment sector, emphasizing its commitment to technology innovation and multi-strategy platform development [1][2]. Group 1: Company Development - Ganyue Investment was established in 2016 and has undergone three phases: quantitative incubation, proprietary fund management, and the establishment of a multi-strategy, multi-portfolio manager platform [2]. - The company currently manages approximately 1.9 billion yuan, with teams focused on quantitative stocks, convertible bonds, subjective futures, arbitrage, and asset allocation [2]. Group 2: Technological Innovation - Ganyue Investment has formed an AI research team composed of personnel from major internet companies, focusing on "AI + securities" to enhance research efficiency and reduce repetitive manual tasks [2][3]. - The company has made significant hardware investments, establishing a substantial independent data center to support the development and iteration of quantitative strategies [2]. - Ganyue Investment is exploring the transformation of investment processes through AI technology, aiming to automate the conversion of research reports and academic papers into effective factors or models [3]. Group 3: Corporate Social Responsibility - Ganyue Investment adopts a subtle approach to corporate social responsibility, focusing on long-term support for education and youth talent development through donations and scholarships [4][5]. - The company encourages employee participation in volunteer services and supports employee-initiated public welfare projects, embedding social responsibility into its corporate culture [4][5]. Group 4: Trust and Industry Development - The "Starry Navigation Plan" provides a platform for private equity institutions to showcase their value and build trust with investors and partners [6]. - Ganyue Investment's development path from quantitative incubation to platform operation exemplifies the potential for professional and diversified growth in the private equity sector [6].

近日，"中国银河证券·中国证券报私募行业星耀领航计划"调研团队走进艮岳投资，公司合伙人蔡群接 受了中国证券报记者的专访，分享了公司在量化投资领域的深耕、对科技创新的探索、多策略平台化发 展的实践，以及他对企业社会责任的理解。 其次，公司在硬件投入上不遗余力。公司位于杭州萧山世纪城，自建了规模可观的独立机房，在算力等 硬件基础设施上进行了超前投入，为量化策略的研发与迭代筑牢底层基础。 最后，公司积极探索AI技术对投资流程的改造。蔡群分享了一个具体案例：公司曾推行"实习生计划"， 试图通过人海战术挖掘因子，但效果有限。生成式AI技术兴起后，公司利用自研及外部工具，显著提 升了研究效率。"使用AI技术一方面降低了实习生需求，另一方面能够让因子验证更高效。"他表示，公 司未来的目标是探索将前沿研报、学术论文自动转化为有效因子或模型，但目前该探索仍处于初级阶 段。 对于量化私募是否会完全转型为科技公司的问题，蔡群持开放态度。他认为，量化本身具有较强的科技 属性，公司氛围也已趋向科技化，倡导"人人用AI"。但作为平台型公司，其策略包容性更强，未来的定 位将是做量化、主观等多种策略的融合体。 践行责任于无声处 "星耀领航计 ...

● 本报记者 刘英杰 最后，公司积极探索AI技术对投资流程的改造。蔡群分享了一个具体案例：公司曾推行"实习生计划"， 试图通过人海战术挖掘因子，但效果有限。生成式AI技术兴起后，公司利用自研及外部工具，显著提 升了研究效率。"使用AI技术一方面降低了实习生需求，另一方面能够让因子验证更高效。"他表示，公 司未来的目标是探索将前沿研报、学术论文自动转化为有效因子或模型，但目前该探索仍处于初级阶 段。 对于量化私募是否会完全转型为科技公司的问题，蔡群持开放态度。他认为，量化本身具有较强的科技 属性，公司氛围也已趋向科技化，倡导"人人用AI"。但作为平台型公司，其策略包容性更强，未来的定 位将是做量化、主观等多种策略的融合体。 "参考美国成熟市场，头部量化机构多采用多PM平台模式。"蔡群表示，当前私募行业经营主体众多， 基金经理流动性较高。平台化模式能更好地抵御由单一策略或市场周期带来的波动，保障公司经营的稳 定性。目前，公司管理规模约19亿元，旗下拥有多组量化股票、可转债、主观期货、套利及资产配置团 队。 在科技金融与赋能科创方面，艮岳投资的实践务实且具有前瞻性，蔡群向记者介绍了公司在三个方面的 探索。 首先，艮 ...

基金管理人在四季报中表示，本基金采用中证红利指数增强型策略进行运作，坚持宽基选股，淡化择时,以数量化分析为基础，多维度选股，行业分散，覆 盖 A 股多板块优质股票。本基金主要采用以"大数据+AI 算法"为基础的量化投资方法，基于对股票市场和上市公司相关数据进行深度挖掘，通过决策树、神 经网络等机器学习和深度学习模型预测个股收益率，再采用组合优化和风险管理模型控制本基金和基准的跟踪误差和最大回撤。 截至2025年四季度末，基金十大重仓股分别是中远海控、中谷物流、兖矿能源、山煤国际、海澜之家、四川路桥、陕西煤业、华阳股份、华夏银行、嘉化能 源。 前十大重仓股变化 100 - % 80 60 40 20 0 2025Q4 – 嘉化能源 –●– 海澜之家 –●– 华阳股份 –●– 中谷物流 –●– 死矿能源 –●– 陕西煤业 –● 制图数据来自恒生聚源数据库 核校：沈楠 AI基金安信红利量化选股股票A（025411）披露2025年四季报，第四季度基金利润312.06万元，加权平均基金份额本期利润0.0182元。报告期内，基金净值 增长率为1.73%，截至四季度末，基金规模为1.58亿元。 截至1月22日，单位净值为1 ...