引子 最近市场有个有趣的现象：一边是融资资金大举加仓煤炭等周期股，药明康德等龙头股获得上亿资金追捧；另一边却是不少散户抱 怨"一买就跌，一卖就涨"。作为一个在量化领域深耕多年的投资者，我深知这背后暗藏的玄机。今天就用我十年来积累的数据经 验，带大家揭开这个市场谜题。 一、融资数据背后的市场密码 11月14日的融资数据显示，煤炭行业以1.34亿元的净买入额领跑全场，药明康德更是获得2.07亿元的大手笔加仓。表面看这是市场 对周期板块和龙头股的认可，但作为一个量化投资者，我更关注的是这些资金流入背后的行为逻辑。 记得我刚入行时也像大多数散户一样，看到大资金流入就盲目跟风。直到后来通过量化系统发现，机构资金的操作远比表面看到的 复杂得多。他们往往会利用这种公开的利好消息作为掩护，进行反向操作。 二、好股票为何总是"折磨人" 任何一只优质股票都面临两个天然矛盾： 1. 跟风盘越来越多 2. 获利盘越来越多 这就好比一辆拥挤的公交车，如果所有人都想挤上去，车子就会超载；如果所有人都想下车，车子就会空驶。聪明的司机（主力机 构）会通过反复开关车门（洗盘）来控制乘客数量。 我用量化系统观察过上百只牛股的走势，发现它们都有一 ...

Core Viewpoint - The article discusses the performance and potential of the CSI A500 Index in the context of the A-share market, highlighting its superior elasticity compared to the CSI 300 Index and its role as a new investment option for investors [2][5]. Group 1: Market Performance - The CSI A500 Index has shown significant growth this year, outperforming the CSI 300 Index, with historical instances of doubling in value during major market rallies in 2009, 2015, and 2020 [2]. - As of October, the CSI A500 Index has been a focal point for investment products, with notable performance from quantitative strategies, particularly from Jiukun Investment's CSI A500 Index Enhanced Product [2][3]. Group 2: Index Characteristics - The CSI A500 Index, launched in September 2024, includes 500 stocks with large market capitalization and good liquidity, representing a balanced distribution across various industries [5][24]. - It covers 71.2% of total A-share market revenue, 56.1% of market capitalization, and 62.5% of net profit attributable to shareholders, indicating a broad market representation despite comprising less than 10% of the total stock count [5][25]. Group 3: Investment Strategy - The combination of the CSI A500 Index with quantitative strategies offers advantages such as risk diversification, capturing new alpha opportunities in emerging industries, and enhancing liquidity [6][7][8]. - Jiukun Investment's approach emphasizes long-term stability and adaptability in various market conditions, leveraging its extensive experience in quantitative investment [11][15]. Group 4: Future Outlook - The CSI A500 Index is positioned as a key area for quantitative investment strategies, with expectations for continued growth and innovation in investment approaches [15][30]. - The index's active trading and diverse industry representation align well with the principles of quantitative investment, making it a favorable choice for investors seeking to capitalize on market trends [15][31].

Core Insights - The article highlights the insights shared by Qian Cheng, chairman of Shanghai Kuan Investment Asset Management Co., during an investment forum, focusing on his experience in quantitative trading and market analysis [1] Group 1: Investment Strategy - Qian Cheng emphasizes the importance of an all-weather strategy, originally developed by Bridgewater Associates, which involves diversifying investments across low-correlation assets such as stocks, bonds, gold, and commodities to achieve stable long-term returns [1] - The strategy is increasingly adopted by major asset management institutions both domestically and internationally [1] Group 2: Market Analysis - Qian notes the inverse volatility relationship between the CSI 300 Index and treasury futures, suggesting that incorporating commodities and gold can enhance the risk-adjusted performance of investment portfolios [1] - He believes that the commodity market is poised for cyclical opportunities in the near future [1] Group 3: Trading Philosophy - The trading philosophy advocated by Qian includes focusing on key sectors during bull markets and decisively taking profits at market peaks to avoid over-reliance on quantitative logic [1] - Asset management firms should prioritize absolute returns and invest in research and strategy optimization to create long-term value for clients [1] - Qian stresses the necessity of maintaining risk control and trend judgment to sustain a competitive edge in the industry amid market fluctuations [1]

为落实《推动公募基金高质量发展行动方案》， 10 月底，公募基金业绩比较基准征求意见稿公布， 11 月 4 日，改革加速落地，业绩比较基准要素一类库、二类库名录已经下发。 业内期待已久的业绩"尺"与"锚"有了标准。 当产品的 " 人设 " 被基准牢牢锁定后，对于投资者而言，更关键问题或许是回答：自身投资目标应该选择怎样 的锚点？ 如果是主动权益产品的投资，一个朴素的准则，或许应该是跟上，或者跑赢平均水平。 跑赢不难，难的是持续跑赢 首先，怎么定义市场平均？ 如果自身目标只是跑赢沪深 300 或者中证 A500 之类的宽基指数，选择相应的指数增强产品，大概率可以满足 目标。但是如果投资主动权益基金，所谓"平均"水平，目前使用较多的是 Wind 偏股混合基金指数（ 885001 ），这是 Wind 根据市场上所有成立时间超过 3 个月的偏股混合型基金等权编制的，大体上反映国内偏股混合 型基金的整体表现。 从近十年的表现来看，偏股混基金指数能持续稳定跑赢市场主流宽基指数。某种程度上，这种"超额"，也是主动 权益基金这类群体的阿尔法体现。 | 年度 | 偏股混合型基 金指数 | 万得全A | 沪深300 | 中证50 ...

Core Insights - The article discusses the advancements made by Galaxy Fund's quantitative team in deep quantitative stock selection research, emphasizing the shift from traditional linear analysis to nonlinear analysis for better market insights and investment opportunities [1][2] Group 1: Quantitative Research Strategies - The quantitative research approach combines linear and nonlinear strategies, utilizing multi-factor models alongside nonlinear machine learning models to achieve stable excess returns and reduce tracking errors [1][2] - The team has developed strategies that include both linear methods, primarily multi-factor models, and nonlinear methods such as XGBoost and LightGBM, which enhance the model's adaptability to market changes [2][3] Group 2: Neural Network Development - The development of complex neural network learning is highlighted, where the approach integrates long-term rules with short-term information to improve the training of supervised learning models [3] - The focus is on extracting features from raw data while addressing the noise present in the data, which aids in the model's ability to adapt quickly to market fluctuations [3] Group 3: Satellite Strategies - To further enhance market adaptability, satellite strategies are employed, including dividend selection and large-cap growth selection, which target specific market characteristics [4] - The dividend selection strategy focuses on high dividend yield stocks, while the large-cap growth strategy emphasizes stocks with large market capitalization and high growth potential [4] Group 4: Risk Management and Product Development - A financial risk management strategy has been developed to mitigate unexpected impacts from risk events, forming a comprehensive quantitative strategy system [5] - The Galaxy Fund has launched two index enhancement products: the Galaxy CSI 300 Index Enhanced Fund and the Galaxy CSI A500 Index Enhanced Fund, with plans to issue the Galaxy CSI 800 Index Enhanced Fund, which offers a balanced representation of both large-cap and mid-cap growth styles [5]

========= Content: --------- <doc id='1'>量化周报 科创 50 即将确认日线下跌，风格切换正在进行 科创 50 即将确认日线下跌，风格切换正在进行。本周（11.10-11.14）， 大盘横盘震荡，上证指数全周收跌 0.18%。在此背景下，汽车确认日线级 别下跌，农林牧渔、消费者服务迎来日线级别上涨。市场的本轮上涨自 4 月 7 日以来，日线级别反弹已经持续了 7 个多月，反弹幅度也基本在 30% 左右，各大指数和板块的上涨基本都轮动了一遍，超 2/3 的行业日线级别 上涨处于超涨状态，几乎所有的规模指数及一半以上的行业更是走出了复 杂的 9-17 浪的上涨结构，而食品饮料、医药、商贸零售、汽车也已经形成 了日线级别下跌，军工、传媒也有较大概率将确认日线级别下跌。因此我 们认为本轮日线级别上涨大概率已临近尾声。此外，创业板、科创 50 自 6 月份以来的上涨短期内已基本见到顶部，科创 50 即将迎来日线级别下 跌，未来科技板块大概率会是震荡调整的态势，风格切换正在进行。中期 来看，上证指数、上证 50、沪深 300、中证 500、深证成指、创业板指、 科创 50 纷纷确认周线级别上涨，而且在日线上只走出了 3 浪结构，中期 牛市刚刚开始；此外，已有 27 个行业处于周线级别上涨中，且 19 个行业 周线上涨走了 1-3 浪结构，因此我们认为本轮牛市是个普涨格局。中期对 于投资者而言，仍然可以逆势布局。</doc> <doc id='2'>A 股景气指数观察。截至 2025 年 11 月 14 日，A 股景气指数为 20.94， 相比 2023 年底上升 15.51，当前处于上升周期中。 A 股情绪指数观察。当前 A 股情绪见底指数信号：空，A 股情绪见顶指数 信号：空，综合信号为：空。 指数增强组合本周表现尚可。中证 500 增强组合跑赢基准 0.66%，沪深 300 增强组合跑输基准 0.58%。 风格上，当前残差波动率因子占优。从纯因子收益来看，本周保险、医药、 有色金属等行业因子相对市场市值加权组合跑出较高超额收益，计算机、 汽车等行业因子回撤较多；风格因子中，残差波动率因子超额收益较高， 市值呈较为显著的负向超额收益。从近期因子表现来看，高杠杆股表现优 异，市值、成长等因子表现不佳。 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。</doc> <doc id='3'>作者 分析师 刘富兵 执业证书编号：S0680518030007 邮箱：liufubing@gszq.com 分析师 沈芷琦 执业证书编号：S0680521120005 邮箱：shenzhiqi@gszq.com 分析师 张国安 执业证书编号：S0680524060003 邮箱：zhangguoan@gszq.com 分析师 赵博文 执业证书编号：S0680524070004 邮箱：zhaobowen@gszq.com 分析师 汪宜生 执业证书编号：S0680525070003 邮箱：wangyisheng@gszq.com 研究助理 阮俊烨 执业证书编号：S0680124070019 邮箱：ruanjunye@gszq.com 相关研究 1、《量化分析报告：择时雷达六面图：本周基本面改善， 拥挤度下降》 2025-11-08 2、《量化分析报告：六周期框架下的多资产 ETF 配置》 2025-11-05 3、《量化点评报告：十一月配置建议：关注小盘+价值 的均衡配置》 2025-11-03</doc> <doc id='4'> | 1. 市场走势分析 4 | | | --- | --- | | 1.1 科创 即将迎来日线下跌，风格切换正在进行 50 4 | | | 1.2 创业板短期或已基本见顶 5 | | | 2. 市场行业分析 6 | | | 2.1 中期看多煤炭、房地产、石油石化、消费者服务 6 | | | 2.2 汽车确认日线下跌，农林牧渔、消费者服务迎来日线上涨 7 | | | 3. 市场景气与情绪观察 8 | | | 3.1 A 8 | 股景气指数观察 | | 3.2 A 股情绪指数观察 9 | | | 4. 情绪指标择时和主题投资机会 11 | | | 4.1 半导体概念股机会 11 | | | 4.2 中证 500 增强组合 11 | | | 4.3 沪深 300 增强组合 14 | | | 5. 市场风格分析 15 | | | 5.1 风格因子表现 15 | | | 5.2 市场主要指数收益风格归因 17 | | | 风险提示 18 | | | 附录： 19 | | | 指数分析及投资建议 19 | | | 行业分析及投资建议 19 | |</doc> <doc id='5'> | 图表 | 1： | 上证综指走势结构图 | | 4 | | --- | --- | --- | --- | --- | | 图表 | 2： | 上证 50 | 走势结构图 | 4 | | 图表 | 3： | 沪深 300 | 走势结构图 | 5 | | 图表 | 4： | 中证 500 | 走势结构图 | 5 | | 图表 | 5： | 中证 1000 | 走势结构图 | 5 | | 图表 | 6： | 深证成指走势结构图 | | 5 | | 图表 | 7： | 创业板指走势结构图 | | 6 | | 图表 | 8： | | 消费者服务中期走势结构图 | 6 | | 图表 | 9： | 煤炭中期走势结构图 | | 6 | | 图表 | 10： | | 石油石化中期走势结构图 | 7 | | 图表 | 11： | | 房地产中期走势结构图 | 7 | | 图表 | 12： | | 当前下行周期与历史平均趋势（横坐标： 持续天数） | 8 | | 图表 | 13： | A 股景气度指数 | | 9 | | 图表 | 14： | | 波动-成交情绪时钟收益统计（沪深 300） | 9 | | 图表 | 15： | A | 股情绪指数（见底预警指数） 10 | | | 图表 | 16： | A | 股情绪指数（见顶预警指数） 10 | | | 图表 | 17： | A | 股情绪指数系统择时表现 11 | | | 图表 | 18： | 半导体概念股 | 11 | | | 图表 | 19： | 中证 500 | 增强组合表现 12 | | | 图表 | 20： | 中证 500 | 增强组合持仓明细 12 | | | 图表 | 21： | 沪深 300 | 增强组合表现 14 | | | 图表 | 22： | 沪深 300 | 增强组合持仓明细 14 | | | 图表 | 23： | | 近一周十大类风格因子暴露相关性 16 | | | 图表 | 24： | | 近一周十大类风格纯因子收益率 16 | | | 图表 | 25： | | 近一周行业纯因子收益率 16 | | | 图

"比如，XGBoost可以对因子的重要性进行展示，通过排序帮助我们识别哪些因子更加重要，增强模型 对市场变化的适应能力。尤其是在今年的结构化行情下，非线性策略能够抓住一些弹性品种的机 会。"罗博表示。 □本报记者 王鹤静 为适应复杂的市场环境，银河基金量化团队近年来在深度量化选股研究领域持续深耕，突破传统线性分 析对历史回测分析的局限，通过非线性分析方式，更加精准地分析市场，挖掘其中的投资机遇。 日前，银河基金量化与FOF投资部总监助理、基金经理罗博在接受中国证券报记者采访时介绍了量化研 究的新思路。在指数样本增强方面，罗博主要采取线性和非线性相结合的方式，由多因子模型与非线性 的机器学习模型互相协作，力争获得相对稳健的超额收益；同时，由于模型间相关性较低，力争有效降 低整体组合的跟踪误差。 开发深度神经网络学习 罗博具有21年证券从业经验、15年公募基金管理经验，长期扎根于指数与量化投资领域。随着市场环境 持续发生变化，罗博意识到，量化投资仅仅依靠线性分析把握市场长期规律愈发难以支撑，在行业趋势 从线性向非线性过渡的过程中，需要不断学习非线性分析技术，紧跟市场变化。 经过近年来的逐步积累和完善，目前罗博针对 ...

黄志钢现任南华基金总经理助理兼量化投资部总经理。这位拥有17年量化投资经验的"老将"是南开大学 金融学硕士，曾历任国联安基金、金鹰基金等重要职务。 黄志钢对记者表示，他的量化投资框架可以概括为"价值选股，双重轮动"。价值选股方面，他在量化模 型中提取出的核心因子，包括了DR（股利支付比例）、ROE（净资产收益率）、EP（盈利收益率） 等。预测每家公司的ROE和EP，是量化模型运作的第一步，第二步是将该结果代入公式计算出IR（潜 在收益率）值，再根据IR值进行排序，选择排名相对靠前的股票构建投资组合。 黄志钢指出，这种方法旨在寻找价值投资中的好公司、好价格。不同于人为主观层面的判断，量化投资 具有相对客观、高效、纪律性强等优点。在具体操作中，将企业未来ROE和EP作为衡量"好公司"和"好 价格"的两个核心指标，将其代入长期研究形成的系列模型公式中，计算出该只股票的潜在收益率，以 完成筛选。在价值定价的同时，黄志钢还会关注个股的"安全边际"构建。黄志钢表示，在他的量化模型 中，会有一系列构建"安全边际"的方法，如估值水平低、低市盈率、高股息等指标。 需要指出的是，按照这样的方式选出来的股票，并不是固定不变的，而是 ...

□本报记者 王鹤静 为适应复杂的市场环境，银河基金量化团队近年来在深度量化选股研究领域持续深耕，突破传统线性分 析对历史回测分析的局限，通过非线性分析方式，更加精准地分析市场，挖掘其中的投资机遇。 日前，银河基金量化与FOF投资部总监助理、基金经理罗博在接受中国证券报记者采访时介绍了量化研 究的新思路。在指数样本增强方面，罗博主要采取线性和非线性相结合的方式，由多因子模型与非线性 的机器学习模型互相协作，力争获得相对稳健的超额收益；同时，由于模型间相关性较低，力争有效降 低整体组合的跟踪误差。 开发深度神经网络学习 罗博具有21年证券从业经验、15年公募基金管理经验，长期扎根于指数与量化投资领域。随着市场环境 持续发生变化，罗博意识到，量化投资仅仅依靠线性分析把握市场长期规律愈发难以支撑，在行业趋势 从线性向非线性过渡的过程中，需要不断学习非线性分析技术，紧跟市场变化。 在简单的神经网络学习基础上，罗博做了进一步的开发和挖掘，看好复杂神经网络学习。"简单的神经 网络学习主要是根据原始数据来提取个股的特征，用未来一段时间的预期收益率作为标签，进行有监督 的学习。但原始数据可能存在较大的'噪音'，很难训练出一个收 ...

Core Insights - The rapid development of AI technology is significantly enhancing the power of quantitative investment, leading to increased market attention on public quantitative investment strategies [1] - Huang Zhigang, Assistant General Manager and Head of Quantitative Investment at Nanhua Fund, emphasizes the limitations of traditional multi-factor models in quantitative investment, which are primarily based on historical data and fail to address long-term market effectiveness [1][4] - Huang identifies three critical issues that an excellent quantitative investment model must solve: constructing investment safety margins, identifying value traps, and reasonably defining company prices [4][5] Group 1: Investment Strategy - Huang's quantitative investment framework is summarized as "value stock selection and dual rotation," focusing on core factors such as Dividend Payout Ratio (DR), Return on Equity (ROE), and Earnings Yield (EP) [2] - The first step in the quantitative model involves predicting each company's ROE and EP, followed by calculating the Potential Return (IR) and ranking stocks based on IR values to build an investment portfolio [2][4] - The model aims to find good companies at good prices, leveraging the objectivity, efficiency, and discipline of quantitative investment over subjective human judgment [2][4] Group 2: Stock Selection and Risk Management - Stocks selected through this method are not static; they are continuously adjusted based on changing factors, with a focus on building a stock pool from those that have declined significantly over the past 3 to 5 years [3] - Huang employs a dual approach to avoid value traps and select stocks with low price-to-earnings ratios, low price-to-book ratios, and high dividend yields to provide safety margins [5][7] - The investment goal is to balance between "good companies" and "good prices," seeking long-term performance advantages rather than focusing on short-term results [5] Group 3: Performance and Market Position - As of now, Huang manages four funds with a total scale exceeding 1 billion yuan, with notable performance metrics such as a net value growth rate of over 87% for Nanhua Fenghui Mixed A since inception [4] - Huang acknowledges the increasing competition in the quantitative investment space, which makes it more challenging to obtain alpha, necessitating continuous updates and factor exploration in quantitative models [4][7] - The domestic quantitative investment market is still developing compared to mature foreign markets, with public quantitative investment expected to gradually reveal its advantages in fundamental research [7]