（编辑 丛可心） 证券日报网讯 1月9日，北玻股份发布公告称，公司2026年1月8日完成控股子公司洛阳北玻高温电窑智 能装备有限公司工商登记，注册资本1000万元，聚焦陶瓷等工业电热高温装备研发制造，预计拓展建筑 外新增长曲线。 ...

证券代码：002613 证券简称：北玻股份 公告编号：2026001 洛阳北方玻璃技术股份有限公司 关于公司对外投资设立子公司的进展公告 本公司及董事会全体成员保证信息披露内容的真实、准确和完整，没有虚假记载、误导性陈述或重大遗漏。 洛阳北方玻璃技术股份有限公司（以下简称"公司"）于 2025 年 12 月 22 日召开的第九届董 事会第四次会议审议通过了《关于公司对外投资设立控股子公司的议案》，同意设立控股子公司洛 阳北玻高温电窑智能装备有限公司，该子公司聚焦建筑行业以外的陶瓷等工业装备制造领域，专注 用于前述领域的电热高温工业电窑、电炉、电烘炉、电熔炉等设备技术的研发、生产经营与技术支 持服务。具体内容详见公司于 2025 年 12 月 23 日在《证券时报》《上海证券报》和巨潮资讯网 （http://www.cninfo.com.cn）披露的相关公告。 2026 年 1 月 8 日，公司完成上述子公司的工商登记手续，并取得了当地市场监督管理局核发 的《营业执照》，现将有关登记情况公告如下： 名 称：洛阳北玻高温电窑智能装备有限公司 统一社会信用代码：91410323MAK443QK6J 住 所：河南省洛 ...

证券之星消息，1月8日玻璃玻纤板块较上一交易日上涨0.44%，九鼎新材领涨。当日上证指数报收于 4082.98，下跌0.07%。深证成指报收于13959.48，下跌0.51%。玻璃玻纤板块个股涨跌见下表： | 代码 | 名称 | 主力净流入(元) | 主力净占比 游资净流入 (元) | | 游资净占比 散户净流入 (元) | | 散户净占比 | | --- | --- | --- | --- | --- | --- | --- | --- | | 002201 | 九鼎新材 | 2.98亿 | 21.77% | -7735.78万 | -5.66% | -2.20 Z | -16.11% | | 002080 | 中材科技 | 2.21 乙 | 11.24% | -4891.87万 | -2.49% | -1.72 Z | -8.75% | | 603601 | 再升科技 | 6625.19万 | 2.16% | -1547.87万 | -0.50% | -5077.32万 | -1.65% | | 600176 | 中国巨石 | 1212.82万 | 1.67% | -1442.22万 | -1.99% | ...

证券之星消息，1月7日玻璃玻纤板块较上一交易日上涨0.1%，宏和科技领涨。当日上证指数报收于 4085.77，上涨0.05%。深证成指报收于14030.56，上涨0.06%。玻璃玻纤板块个股涨跌见下表： | 代码 | 名称 | 主力净流入(元) | 主力净占比 游资净流入 (元) | | 游资净占比 散户净流入(元) | | 散户净占比 | | --- | --- | --- | --- | --- | --- | --- | --- | | 603256 宏和科技 | | 9391.29万 | 7.89% | -1753.57万 | -1.47% | -7637.72万 | -6.42% | | 301526 | 国际复材 | 7576.02万 | 7.99% | 2348.46万 | 2.48% | -9924.48万 | -10.47% | | 601636 旗滨集团 | | 1772.76万 | 4.75% | -210.02万 | -0.56% | -1562.74万 | -4.19% | | 618000 | 耀皮玻璃 | 1143.91万 | 7.22% | -461.39万 | -2.91% ...

Group 1 - The core point of the article is that Beibo Co., Ltd. (002613) confirmed on an interactive platform that it is a joint-stock company with a natural person as its largest shareholder as of September 30, 2024 [1]

Quantitative Models and Construction Methods 1. Model Name: GAN_GRU - **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 construct a stock selection factor[4][13][14] - **Model Construction Process**: 1. **GAN Component**: - The generator (G) learns the real data distribution and generates realistic samples from random noise \( z \) (Gaussian or uniform distribution). The generator's loss function is: $$ L_{G} = -\mathbb{E}_{z\sim P_{z}(z)}[\log(D(G(z)))] $$ where \( D(G(z)) \) represents the discriminator's probability of classifying generated data as real[24][25][26] - The discriminator (D) distinguishes real data from generated data. Its loss function is: $$ L_{D} = -\mathbb{E}_{x\sim P_{data}(x)}[\log D(x)] - \mathbb{E}_{z\sim P_{z}(z)}[\log(1-D(G(z)))] $$ where \( D(x) \) is the probability of real data being classified as real, and \( D(G(z)) \) is the probability of generated data being classified as real[27][29][30] - GAN training alternates between optimizing \( G \) and \( D \) until convergence[30] 2. **GRU Component**: - Two GRU layers (GRU(128, 128)) are used to encode time-series features, followed by a Multi-Layer Perceptron (MLP) with layers (256, 64, 64) to predict returns. The final output \( pRet \) is used as the stock selection factor[22] 3. **Feature Input and Processing**: - Input features include 18 price-volume characteristics (e.g., closing price, turnover, etc.) sampled over the past 400 days, with a shape of \( 40 \times 18 \) (40 days of features)[18][19][37] - Features undergo outlier removal, standardization, and cross-sectional normalization[18] 4. **Training Details**: - Training-validation split: 80%-20% - Semi-annual rolling training (June 30 and December 31 each year) - Hyperparameters: batch size equals the number of stocks, Adam optimizer, learning rate \( 1e-4 \), IC loss function, early stopping (10 rounds), max training rounds (50)[18] 5. **Stock Selection**: - Stocks are filtered to exclude ST stocks and those listed for less than six months[18] - **Model Evaluation**: The GAN_GRU model effectively captures price-volume time-series features and demonstrates strong predictive power for stock returns[4][13][22] --- Model Backtesting Results 1. GAN_GRU Model - **IC Mean**: 0.1119*** (2019-2025)[4][41] - **ICIR (non-annualized)**: 0.89[42] - **Turnover Rate**: 0.83X[42] - **Recent IC**: 0.0331*** (December 2025)[4][41] - **1-Year IC Mean**: 0.0669***[4][41] - **Annualized Return**: 37.40%[42] - **Annualized Volatility**: 23.39%[42] - **IR**: 1.60[42] - **Maximum Drawdown**: 27.29%[42] - **Annualized Excess Return**: 22.42%[4][42] --- Quantitative Factors and Construction Methods 1. Factor Name: GAN_GRU Factor - **Factor Construction Idea**: The GAN_GRU factor is derived from the GAN_GRU model, leveraging GAN for price-volume feature generation and GRU for time-series encoding[4][13][14] - **Factor Construction Process**: - The GAN generator processes raw price-volume time-series features (\( Input\_Shape = 40 \times 18 \)) and outputs transformed features with the same shape (\( Input\_Shape = 40 \times 18 \))[37] - The GRU component encodes these features into a predictive factor for stock selection[22] - The factor undergoes industry and market capitalization neutralization and standardization[22] - **Factor Evaluation**: The GAN_GRU factor demonstrates robust performance across various industries and time periods, with significant IC values and excess returns[4][41] --- Factor Backtesting Results 1. GAN_GRU Factor - **IC Mean**: 0.1119*** (2019-2025)[4][41] - **ICIR (non-annualized)**: 0.89[42] - **Turnover Rate**: 0.83X[42] - **Recent IC**: 0.0331*** (December 2025)[4][41] - **1-Year IC Mean**: 0.0669***[4][41] - **Annualized Return**: 37.40%[42] - **Annualized Volatility**: 23.39%[42] - **IR**: 1.60[42] - **Maximum Drawdown**: 27.29%[42] - **Annualized Excess Return**: 22.42%[4][42] 2. Industry-Specific Performance - **Top 5 Industries by Recent IC (October 2025)**: - Social Services: 0.4243*** - Coal: 0.2643*** - Environmental Protection: 0.2262*** - Retail: 0.1888*** - Steel: 0.1812***[4][41][42] - **Top 5 Industries by 1-Year IC Mean**: - Social Services: 0.1303*** - Steel: 0.1154*** - Non-Bank Financials: 0.1157*** - Retail: 0.1067*** - Building Materials: 0.1017***[4][41][42] 3. Industry-Specific Excess Returns - **Top 5 Industries by December 2025 Excess Returns**: - Banking: 4.30% - Real Estate: 3.51% - Environmental Protection: 2.18% - Retail: 1.76% - Machinery: 1.71%[2][45] - **Top 5 Industries by 1-Year Average Excess Returns**: - Banking: 2.12% - Real Estate: 1.93% - Environmental Protection: 1.50% - Retail: 1.46% - Machinery: 1.23%[2][46]

Market Overview - The glass fiber sector experienced a decline of 1.83% on December 29, with Jiuding New Materials leading the drop [1] - The Shanghai Composite Index closed at 3965.28, up 0.04%, while the Shenzhen Component Index closed at 13537.1, down 0.49% [1] Stock Performance - Notable stock performances in the glass fiber sector include: - Honghe Technology: Closed at 38.02, up 1.12%, with a trading volume of 238,900 shares and a transaction value of 898 million [1] - Shandong Glass Fiber: Closed at 7.48, up 0.67%, with a trading volume of 65,300 shares and a transaction value of 48.48 million [1] - Jiuding New Materials: Closed at 11.21, down 9.96%, with a trading volume of 1,544,900 shares and a transaction value of 1.787 billion [2] Capital Flow - The glass fiber sector saw a net outflow of 1.142 billion from institutional investors, while retail investors had a net inflow of 850 million [2] - The capital flow for specific stocks indicates: - Jiuding New Materials had a significant net outflow of 4.216 million from institutional investors [3] - Shandong Glass Fiber experienced a net inflow of 535.81 thousand from institutional investors [3] Summary of Individual Stocks - Key stocks in the glass fiber sector and their respective capital flows include: - Jiuding New Materials: -4.216 million from institutions, -9.96% change [2][3] - Shandong Glass Fiber: +535.81 thousand from institutions, +0.67% change [2][3] - China Jushi: -3.01% change with a transaction value of 898 million [2]

Market Performance - The glass and fiberglass sector increased by 0.24% compared to the previous trading day, with Jiuding New Materials leading the gains [1] - The Shanghai Composite Index closed at 3963.68, up 0.1%, while the Shenzhen Component Index closed at 13603.89, up 0.54% [1] Stock Performance - Jiuding New Materials (002201) closed at 12.45, up 9.98% with a trading volume of 437,000 shares and a transaction value of 544 million [1] - Zais Technology (603601) also rose by 9.98% to close at 13.34, with a trading volume of 4.43 million shares and a transaction value of 5.795 billion [1] - Other notable performers include Sanxia New Materials (600293) up 5.66% and Jinjing Technology (600586) up 2.10% [1] Capital Flow - The glass and fiberglass sector experienced a net outflow of 1.389 billion from institutional investors, while retail investors saw a net inflow of 1.149 billion [2] - The overall capital flow indicates that retail investors are actively buying into the sector despite the institutional outflow [2] Individual Stock Capital Flow - Sanxia New Materials (600293) had a net inflow of 21.0753 million from institutional investors, while retail investors contributed a net inflow of 1.824 million [3] - Jiuding New Materials (002201) saw a net outflow of 17.2338 million from institutional investors but a net inflow of 12.6057 million from retail investors [3] - Other stocks like Yao Pi Glass (618009) and Changhai Co. (300196) faced significant net outflows from both institutional and retail investors [3]

Group 1 - The glass and fiberglass sector increased by 0.17% on December 25, with Jiuding New Materials leading the gains [1] - The Shanghai Composite Index closed at 3959.62, up 0.47%, while the Shenzhen Component Index closed at 13531.41, up 0.33% [1] - Jiuding New Materials saw a closing price of 11.32, with a significant increase of 10.01% and a trading volume of 65,200 shares, amounting to 73.80 million yuan [1] Group 2 - The glass and fiberglass sector experienced a net outflow of 294 million yuan from institutional investors, while retail investors saw a net inflow of 432 million yuan [2] - The trading data indicates that Jiuding New Materials had a net inflow of 30.28 million yuan from institutional investors, representing 41.03% of its trading volume [3] - In contrast, China Jushi experienced a decline of 1.19% in its stock price, closing at 16.59 with a trading volume of 439,900 shares, totaling 73.20 million yuan [2]

Core Viewpoint - The company is establishing a new subsidiary to capitalize on market opportunities in the industrial equipment manufacturing sector, focusing on green transformation and intelligent upgrades [1][2] Group 1: Investment Details - The company announced the establishment of a new subsidiary, Luoyang North Glass High-Temperature Electric Kiln Intelligent Equipment Co., Ltd., with a registered capital of 10 million yuan [1] - The company will contribute 7.5 million yuan, representing 75% of the registered capital, while the employee stockholding platform will contribute 2.5 million yuan, representing 25% [1] Group 2: Strategic Focus - The new subsidiary will focus on the industrial equipment manufacturing sector outside of the construction industry, particularly in ceramics [1] - The subsidiary aims to develop and manufacture high-temperature electric heating intelligent production equipment that converts fossil energy such as natural gas and coal gas into clean electric energy [1] Group 3: Strategic Rationale - The investment aligns with the company's future development strategy, enhancing the synergy of the industrial chain and improving core competitiveness and sustainable development capabilities [2] - The collaboration with the employee stockholding platform is intended to share risks and stimulate employee engagement, promoting stable and sustainable company growth [2]