中国质量新闻网讯 据海南省市场监督管理局网站消息，2025年第4季度，海南省市场监督管理局对全省流通领域内外墙用腻子产品进行了监督抽查。本次抽 查了21批次产品，经检验，全部合格。 本次监督抽查依据JG/T 157-2009、JG/T 298-2010、GB18582-2020等标准要求，对下列项目进行了检验:容器中状态、施工性、干燥时间、打磨性、耐碱性、 耐水性、低温贮存稳定性、吸水量、腻子膜柔韧性、初期干燥抗裂性、粘结强度、VOC含量、苯系物总和含量[限苯、甲苯、二甲苯(含乙苯)]、甲醛含量、 总铅(Pb)含量、可溶性重金属含量等。本次抽查未发现有不符合标准要求的项目。 2025年海南省流通领域内外墙用腻子产品质量监督抽查所检项目符合相关标准的产品 | 序 | 产品名称(标称) | 商标(标称) | | 生产日期/批号 | | 生产企业(标称) | | --- | --- | --- | --- | --- | --- | --- | | 号 | | | 规格型号 | (标称) | 被检主体 | | | 1 | 快涂宝净味防碱腻子 | / | Y 15kg/包 | 2025/08/03 | 定安定城业春五 ...

中国质量新闻网讯 据海南省市场监督管理局网站消息，2025年第4季度，海南省市场监督管理局对全省流通领域防水涂料产品进行了监督抽查。本次抽查了 20批次产品，经检验，全部合格。 本次监督抽查依据GB/T 19250-2013、GB/T 23445-2009、JC 1066-2008、GB 23440-2009等标准要求，对下列项目进行了检验:不透水性、断裂伸长率、拉伸 强度、固体含量、粘结强度、定伸时老化(加热老化)、低温柔性、低温弯折性、吸水率、撕裂强度、热处理、挥发性有机化合物(VOC)、苯、甲苯+乙苯+二 甲苯、苯酚、蒽、萘、游离TDI、外观、凝结时间、抗压强度、抗折强度、粘结强度、耐热性、冻融循环等。 | 序 | 产品名称(标称) | 商标(标称) | 规格型号 | 生产日期/批 | 被检主体 | 生产企业(标称) | | --- | --- | --- | --- | --- | --- | --- | | 号 | | | | 号(标称) | | | | 1 灰橡胶(防水涂料) | | 金色荷花+图 | S I E B 18±0.5kg/桶 | 2025/08/21 | 海南云泰防维工程有限公 | ...

Quantitative Models and Construction Methods 1. Model Name: GAN_GRU Model - **Model Construction Idea**: The GAN_GRU model combines Generative Adversarial Networks (GAN) for feature generation and Gated Recurrent Unit (GRU) for time-series feature encoding to create a stock selection factor[4][13][14] - **Model Construction Process**: - **GAN Component**: - The GAN consists of a generator (G) and a discriminator (D). The generator learns the real data distribution and generates realistic samples, while the discriminator distinguishes between real and generated data[23][24] - Generator loss function: $$L_{G} = -\mathbb{E}_{z\sim P_{z}(z)}[\log(D(G(z)))]$$ where \(z\) is random noise, \(G(z)\) is the generated data, and \(D(G(z))\) is the discriminator's output probability for generated data being real[24][25] - Discriminator loss function: $$L_{D} = -\mathbb{E}_{x\sim P_{data}(x)}[\log D(x)] - \mathbb{E}_{z\sim P_{z}(z)}[\log(1-D(G(z)))]$$ where \(x\) is real data, \(D(x)\) is the discriminator's output probability for real data, and \(D(G(z))\) is the discriminator's output probability for generated data[27][29] - GAN training alternates between updating the generator and discriminator parameters through backpropagation[30] - The generator uses an LSTM model to preserve the sequential nature of input features, while the discriminator employs a CNN model to process the 2D structure of the generated features[33][37] - **GRU Component**: - Two GRU layers (GRU(128, 128)) are used, followed by an MLP (256, 64, 64) to output predicted returns (\(pRet\)) as the stock selection factor[22] - Input features include 18 price-volume characteristics (e.g., closing price, turnover rate) sampled over the past 40 days to predict cumulative returns for the next 20 trading days[14][18] - Data preprocessing includes outlier removal, standardization, and cross-sectional normalization[18] - Training is conducted semi-annually with rolling updates, using Adam optimizer, a learning rate of \(1e-4\), and IC as the loss function[18] - **Model Evaluation**: The GAN_GRU model effectively integrates GAN's feature generation capabilities with GRU's time-series encoding, making it suitable for capturing complex price-volume patterns in stock selection[4][13] --- Model Backtesting Results GAN_GRU Model - **IC Mean**: 0.1096*** (2019.02–2026.02)[41] - **ICIR (Non-Annualized)**: 0.87[42] - **Turnover Rate**: 0.82X[42] - **Recent IC**: -0.0105*** (latest period)[41][42] - **1-Year IC Mean**: 0.0517***[41][42] - **Annualized Return**: 38.13%[42] - **Annualized Volatility**: 23.18%[42] - **IR**: 1.64[42] - **Maximum Drawdown**: 27.29%[42] - **Annualized Excess Return**: 22.32%[41][42]

摘要 ■ 投资逻辑 基于大模型对券商年度展望的全面解析 每年的年底到年初，各券商会密集发布关于总量、行业等年度报告。对投资者而言，难以整合大量研报信息从而提取共识点，此外分歧点也同样缺乏量化 对比。大模型工具的出现解决了这一难点，大模型可以帮助分析师快速完成研报数据预处理、观点精准抓取与分类；大模型通过确定共识点与分歧点的判 定规则，系统整合分散观点，量化呈现各券商对板块不同观点的支持率，清晰核心分歧维度。本次研究以大模型为核心分析工具，全面剖析2026年各大板 块年度展望，梳理宏观、策略、固收及七大细分行业的共识与分歧，为投资者提供高效精准的决策参考。 总量观点总结 对于总量观点，我们分别从宏观经济、年度策略、固定收益三个方面分别剖析了各券商分析师的年度展望。 在宏观经济方面，大多数券商认为随着"十五五"政策发力，2026年GDP目标为5%左右；CPI、PPI从低位逐步修复，国内通货膨胀的压力得到缓解；货币 政策维持适度宽松基调，流动性保持合理充裕；财政政策延续积极取向，赤字率维持合理高位；出口保持稳健，贸易顺差维持历史较高水平；国外环境虽 然出现波动，但整体风险可控。 作者：高智威、许坤圣 在年度策略方面 ...

消息面上，东方雨虹在广西成立绿色建材科技公司，经营范围含新材料技术推广服务、新材料技术研 发、建筑防水卷材产品销售等，由东方雨虹全资持股。建材行业尾部出清持续推进，竞争格局优化，龙 头企业迎来发展契机。 2月25日东方雨虹高开后快速上攻，随后整体呈现震荡上行的走势，盘中上行动能充足，多次推动价格 走高；午后13：37左右出现显著拉升，伴随成交量放大，价格进一步抬升，截至13：44分，涨幅为 10.01%，最新价18.91元，总市值451.70亿元，封板资金6.00亿元，成交额12.56亿元，换手率3.57%。 市场围绕东方雨虹的绿色建材布局、海外产能落地以及行业格局优化展开炒作，公司持续在核心领域深 耕，完善全球产能布局，同时行业竞争格局逐步向头部集中。 行业需求结构转变，与城市更新及出口链相关的需求逐步成长，为企业带来新的发展支撑。 ...

- The GAN_GRU factor is based on the GAN_GRU model, which utilizes Generative Adversarial Networks (GAN) for processing volume-price time series features and then employs the GRU model for time series feature encoding to derive the stock selection factor[4][13] - The GAN_GRU model includes two GRU layers (GRU(128, 128)) followed by an MLP (256, 64, 64), with the final output being the predicted return (pRet) used as the stock selection factor[22] - The GAN model consists of a generator and a discriminator. The generator aims to generate data that appears real, while the discriminator aims to distinguish between real and generated data. The generator's loss function is $L_{G} = -\mathbb{E}_{z\sim P_{z}(z)}[\log(D(G(z)))]$ and the discriminator's loss function is $L_{D} = -\mathbb{E}_{x\sim P_{d a t a}(x)}[\log D(x)] - \mathbb{E}_{z\sim P_{z}(z)}[\log(1-D(G(z)))]$[23][24][27] - The GAN_GRU model's training process involves alternating between training the generator and the discriminator until convergence[29][30] - The GAN_GRU factor's performance from February 2019 to February 2026 shows an IC mean of 0.1096, an annualized excess return of 22.32%, and an ICIR (non-annualized) of 0.87[41][42] - The latest IC value as of February 25, 2026, is -0.0105, with a one-year IC mean of 0.0517[41][42] - The top five industries for the GAN_GRU factor in February 2026, based on IC, are Electric Utilities, Retail, Real Estate, Construction, and Basic Chemicals, with IC values of 0.1257, 0.1196, 0.1151, 0.1130, and 0.1063, respectively[44] - The top five industries for the GAN_GRU factor over the past year, based on IC mean, are Steel, Computers, Media, Retail, and Food & Beverage, with IC means of 0.1404, 0.1175, 0.1132, 0.1014, and 0.0989, respectively[44] - The top five industries for the GAN_GRU factor's long positions in February 2026, based on excess returns, are Oil & Petrochemicals, Communications, Electronics, Non-ferrous Metals, and Computers, with excess returns of 7.91%, 3.11%, 3.06%, 2.78%, and 2.78%, respectively[45] - The top five industries for the GAN_GRU factor's long positions over the past year, based on average monthly excess returns, are Real Estate, Retail, Automobiles, Construction, and Consumer Services, with excess returns of 3.83%, 2.04%, 1.93%, 1.50%, and 1.49%, respectively[46] **Performance Metrics of GAN_GRU Factor:** - IC: 0.1096[41][42] - ICIR (non-annualized): 0.87[41][42] - Turnover Rate: 0.82X[41][42] - Recent IC: -0.0105[41][42] - One-year IC: 0.0517[41][42] - Annualized Return: 38.13%[41][42] - Annualized Volatility: 23.18%[41][42] - Information Ratio (IR): 1.64[41][42] - Maximum Drawdown: 27.29%[41][42] - Annualized Excess Return: 22.32%[41][42]

Group 1: Market Performance - The A-share market experienced a comprehensive recovery on February 25, with all three major indices rising collectively and trading activity significantly increasing [1] - The construction and building materials sector was a focal point, with industry leader Oriental Yuhong (002271.SZ) hitting the daily limit up at 18.91 yuan, closing at 18.75 yuan, with a trading volume of 1.657 billion yuan and a market capitalization of 44.788 billion yuan [1] - Oriental Yuhong's stock performance notably outpaced the sector and market indices, becoming a key driver of the building materials sector's rise [1] Group 2: Industry Dynamics - The strong performance of Oriental Yuhong is supported by favorable macro policies in the real estate sector, including measures to stabilize expectations, sales, and project completions, as well as the optimization of purchase and loan restrictions [1] - Infrastructure investment continues to underpin the economy, with major engineering projects commencing, leading to stable demand growth for the building materials industry [1] - The decline in prices of chemical raw materials such as coal and soda ash has further enhanced the company's profit margins [1] Group 3: Company Developments - Oriental Yuhong has made significant strides in its internationalization strategy, with overseas business becoming a crucial growth engine [2] - The company completed the acquisition of 60% of Brazilian Novakem, leveraging its expertise in additives and local channels to penetrate the core Latin American building materials market [2] - The production and logistics R&D base in Dammam, Saudi Arabia, has commenced operations, enhancing the company's localized production and regional supply capabilities [2] Group 4: Domestic Market Expansion - In the domestic market, Oriental Yuhong has established a green materials technology company in Guangxi, aligning with the green building materials policy direction and enhancing its domestic capacity layout [3] - The company has diversified its operations, extending from waterproofing to various sectors including consumer building materials, coatings, and mortar [3] - With the gradual release of overseas capacity and ongoing domestic business expansion, the certainty of profit recovery for Oriental Yuhong has significantly increased [3]

Group 1 - The core point of the news is that Oriental Yuhong conducted a block trade on February 25, with a total of 140,000 shares traded at a price of 17.19 yuan, which is an 8.32% discount compared to the market closing price of 18.75 yuan [1][2] - The total transaction amount for the block trade was 2.4066 million yuan, accounting for 0.15% of the total trading volume on that day [1][2] - The buyer and seller of the shares were both from Everbright Securities Co., Ltd., indicating a potential strategic move within the same brokerage [2]

Core Viewpoint - The renovation and building materials sector experienced growth, closing at 18,828.69 points with an increase of 2.12% [1] Group 1: Stock Performance - Several stocks in the renovation and building materials sector saw price increases, with Keshun Co. leading at a closing price of 8.19 yuan per share, up 14.23% [1] - Meike Home closed at 2.85 yuan per share, marking a rise of 10.04%, ranking second in the sector [1] - Dongfang Yuhong closed at 18.75 yuan per share, with a gain of 9.08%, placing third among renovation and building materials stocks [1] - Conversely, Yueshen Health led the decline with a closing price of 5.27 yuan per share, down 7.22% [1] - Senying Windows closed at 36.43 yuan per share, down 3.24%, ranking second in losses [1] - Haolaike closed at 15.06 yuan per share, with a decrease of 2.59%, ranking third in the decline [1] Group 2: Market Outlook - Huafu Securities indicated that the acceleration of supply-side reforms amid anti-involution expectations may signal a turning point in the building materials capacity cycle [1] - The expectation of declining interest rates is seen as beneficial for restoring home-buying willingness, while storage and urban renewal are expected to enhance home-buying capacity [1] - The marginal recovery in home-buying willingness and capacity is anticipated to increase the probability of stabilization in the real estate market fundamentals, which may also drive the recovery of post-real estate cycle demand [1]

编辑|段炼 杜恒峰 校对|何小桃 | | 影视传媒 | | | | | --- | --- | --- | --- | --- | | | 901.75,-0.65% | | | | | 新闻 大V | 成分 资金 | | | | | 博纳影业 | | 10.34 | -10.01% | 0.00% | | SZ001330 | | | | | | 横店影视 | | | | | | SH603103 | | 28.27 | -10.00% | 0.00% | | 市值龙头10 | | | | | | 中国电影 | | | | | | SH600977 | | 15.32 | -8.26% | +0.39% | | 市值龙头5 | | | | | | 果麦文化 | | 43.05 | -6.62% | -0.02% | | 创 SZ301052 | | | | | | 光线传媒 | | | | | | 创 SZ300251 | | 20.62 | -5.33% | +0.29% | | 业绩龙头1 市值龙头 1 | | | | | 2月25日，A股三大指数全线飘红。截至收盘沪指涨0.72%，深成指涨1.29%， ...