Core Points - The company reported a container throughput of 2.319 million TEUs, representing a year-on-year increase of 1.2% [2] - The expected total cargo throughput for 2025 is 49.878 million tons, with a year-on-year growth of 2.0% [2] - For the period from January to August 2025, the company anticipates a container throughput of 18.037 million TEUs, reflecting a year-on-year increase of 7.5% [2] - The expected cargo throughput for the same period is 385.870 million tons, showing a year-on-year growth of 2.5% [2] - The data provided for August 2025 and the January to August 2025 period are preliminary statistics and may differ from final actual figures [2]

Group 1 - The company Guangzhou Port (601228.SH) expects to achieve a container throughput of 2.319 million TEUs in August 2025, representing a year-on-year growth of 1.2% [1] - The company anticipates a total cargo throughput of 49.878 million tons in August 2025, with a year-on-year increase of 2.0% [1] - For the period from January to August 2025, the company projects a container throughput of 18.037 million TEUs, reflecting a year-on-year growth of 7.5% [1] Group 2 - The expected total cargo throughput from January to August 2025 is 385.870 million tons, indicating a year-on-year growth of 2.5% [1]

证券代码：601228 证券简称：广州港 公告编号：2025-051 债券代码：137812.SH、115012.SH、240489.SH、243016.SH、243145.SH、243396.SH、243619.SH 债券简称：22 粤港 04、23 粤港 01、24 粤港 01、25 粤港 01、25 粤港 02、25 粤港 03、25 粤港 04 广州港股份有限公司 2025 年 8 月份及 1-8 月主要生产数据提示性公告 本公司董事会及全体董事保证本公告内容不存在任何虚假记载、误导性陈述 或者重大遗漏，并对其内容的真实性、准确性和完整性承担法律责任。 2025 年 8 月份，广州港股份有限公司（以下简称"公司"）预计完成集装箱 吞吐量 231.9 万标准箱，同比增长 1.2%；预计完成货物吞吐量 4,987.8 万吨， 同比增长 2.0%。2025 年 1-8 月，公司预计完成集装箱吞吐量 1,803.7 万标准箱， 同比增长 7.5%；预计完成货物吞吐量 38,587.0 万吨，同比增长 2.5%。 本公告所载公司 2025 年 8 月份及 1-8 月的业务数据属于快速统计数据，与 最终实际数据可 ...

Core Viewpoint - Guangzhou Port (601228.SH) expects to achieve a container throughput of 2.319 million TEUs in August 2025, representing a year-on-year increase of 1.2% [1] - The company anticipates a total cargo throughput of 49.878 million tons in the same period, reflecting a year-on-year growth of 2.0% [1] Summary by Relevant Categories Container Throughput - For the period from January to August 2025, the company projects a container throughput of 18.037 million TEUs, which is a year-on-year increase of 7.5% [1] Cargo Throughput - During the same January to August 2025 timeframe, the expected cargo throughput is 385.870 million tons, showing a year-on-year growth of 2.5% [1]

Core Viewpoint - The company anticipates an increase in container throughput and cargo throughput for the year 2025, indicating positive growth trends in its operations [1] Group 1: Container Throughput - The company expects to complete a container throughput of 2.319 million TEUs in August 2025, representing a year-on-year growth of 1.2% [1] - For the period from January to August 2025, the company projects a container throughput of 18.037 million TEUs, reflecting a year-on-year increase of 7.5% [1] Group 2: Cargo Throughput - The company forecasts a cargo throughput of 49.878 million tons in August 2025, which is a year-on-year growth of 2.0% [1] - From January to August 2025, the expected cargo throughput is 386 million tons, showing a year-on-year increase of 2.5% [1]

Core Viewpoint - The Huangsha Aquatic Products Trading Market in Guangzhou is set to relocate to a new facility, the Huangsha Aquatic Center, which will officially open on September 8, 2025, marking a significant transition for the largest aquatic market in South China [1][3]. Group 1: Market Transition - The old market, established in 1994, continues to operate normally with merchants unaware of specific relocation dates, although the announcement has been made [2][3]. - Merchants in the old market express mixed feelings about the move, with some uncertain about the impact on their business and customer base [2][3]. - The relocation is part of a broader urban planning initiative aimed at reducing the environmental and traffic impact of the old market [3]. Group 2: New Market Features - The new market, located at 188 Sha Luo Long Wan Street, has been under development for five years and is nearing completion, with most facilities ready for operation [4][5]. - The new facility will cover approximately 110,000 square meters and aims to integrate trading, logistics, exhibition, e-commerce, and cultural tourism [5][6]. - Innovative features include a centralized cooling, oxygen supply, and seawater system, along with a digital management platform to enhance operational efficiency [5][6]. Group 3: Business Operations - The new market has achieved over 97% occupancy for wholesale operations, covering a full range of aquatic products, and is set to innovate in logistics and dining experiences [6]. - The market aims to become a new landmark for marine culture and tourism in Guangzhou, promoting the city's culinary identity [6].

依据《上海证券交易所公司债券上市规则》等规定，上交所同意广州港股份有限公司2025年面向专业投 资者公开发行公司债券（第四期）于2025年9月3日起在上交所上市，并采取匹配成交、点击成交、询价 成交、竞买成交、协商成交交易方式。该债券证券简称为"25粤港04"，证券代码为"243619"。根据中国 结算规则，可参与质押式回购。 9月2日，上交所发布关于广州港股份有限公司2025年面向专业投资者公开发行公司债券（第四期）上市 的公告。 ...

Quantitative Models and Construction Methods - **Model Name**: GAN_GRU **Model Construction Idea**: The GAN_GRU model combines Generative Adversarial Networks (GAN) for processing volume-price time-series features and Gated Recurrent Unit (GRU) for encoding time-series features to create a stock selection factor[4][13][41] **Model Construction Process**: 1. **GRU Component**: - Input features include 18 volume-price features such as closing price, opening price, turnover, and turnover rate[14][17][19] - Training data consists of the past 400 days of these features, sampled every 5 trading days, forming a 40x18 matrix to predict cumulative returns over the next 20 trading days[18] - Data preprocessing includes outlier removal and normalization at both time-series and cross-sectional levels[18] - Model architecture: Two GRU layers (128, 128) followed by an MLP (256, 64, 64), with the final output being the predicted return (pRet), which serves as the stock selection factor[22] - Training method: Semi-annual rolling training, with training conducted on June 30 and December 31 each year[18] - Optimization: Adam optimizer, learning rate of 1e-4, IC loss function, early stopping after 10 epochs, and a maximum of 50 training epochs[18] 2. **GAN Component**: - GAN consists of a generator (G) and a discriminator (D)[23] - Generator: Uses LSTM to preserve the time-series nature of the input features, transforming random noise into realistic data samples[33][37] - Loss function: $$ L_{G} = -\mathbb{E}_{z\sim P_{z}(z)}[\log(D(G(z)))] $$ where \( z \) represents random noise, \( G(z) \) is the generated data, and \( D(G(z)) \) is the discriminator's output probability[24][25] - Discriminator: Uses CNN to process the two-dimensional volume-price time-series features, distinguishing between real and generated data[33][37] - 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 for real data, and \( D(G(z)) \) is the output for generated data[27][29] - Training: Alternating updates of the generator and discriminator parameters until convergence[30] **Model Evaluation**: The GAN_GRU model effectively captures both time-series and cross-sectional features, leveraging the strengths of GAN and GRU for stock selection[4][13][41] --- Model Backtesting Results - **GAN_GRU Model**: - **IC Mean**: 11.36%[41][42] - **ICIR (Non-Annualized)**: 0.88[42] - **Turnover Rate**: 0.83[42] - **Recent IC**: -2.56%[41][42] - **1-Year IC Mean**: 8.94%[41][42] - **Annualized Return**: 38.09%[42] - **Annualized Volatility**: 23.68%[42] - **IR**: 1.61[42] - **Maximum Drawdown**: 27.29%[42] - **Annualized Excess Return**: 23.52%[41][42] --- Quantitative Factors and Construction Methods - **Factor Name**: GAN_GRU Factor **Factor Construction Idea**: Derived from the GAN_GRU model, this factor encodes volume-price time-series features to predict stock returns[4][13][41] **Factor Construction Process**: - The factor is generated using the output of the GAN_GRU model, which combines GAN-based feature generation and GRU-based time-series encoding[4][13][41] - The factor undergoes industry and market capitalization neutralization, as well as standardization, before being used for testing[22] **Factor Evaluation**: The GAN_GRU factor demonstrates strong predictive power across various industries, with consistent outperformance in recent years[4][13][41] --- Factor Backtesting Results - **GAN_GRU Factor**: - **IC Mean**: 11.36%[41][42] - **ICIR (Non-Annualized)**: 0.88[42] - **Turnover Rate**: 0.83[42] - **Recent IC**: -2.56%[41][42] - **1-Year IC Mean**: 8.94%[41][42] - **Annualized Return**: 38.09%[42] - **Annualized Volatility**: 23.68%[42] - **IR**: 1.61[42] - **Maximum Drawdown**: 27.29%[42] - **Annualized Excess Return**: 23.52%[41][42]

据证券之星公开数据整理，近期广州港（601228）发布2025年中报。截至本报告期末，公司营业总收入 69.09亿元，同比上升1.39%，归母净利润5.52亿元，同比下降9.12%。按单季度数据看，第二季度营业 总收入34.92亿元，同比下降2.37%，第二季度归母净利润2.9亿元，同比上升0.14%。本报告期广州港公 司应收账款体量较大，当期应收账款占最新年报归母净利润比达144.48%。 本次财报公布的各项数据指标表现一般。其中，毛利率22.51%，同比减11.18%，净利率9.61%，同比减 10.25%，销售费用、管理费用、财务费用总计9.19亿元，三费占营收比13.31%，同比增8.77%，每股净 资产2.79元，同比增2.9%，每股经营性现金流0.25元，同比增19.29%，每股收益0.07元，同比减8.75% 财报体检工具显示： 建议关注公司现金流状况（货币资金/流动负债仅为64.93%） 建议关注公司债务状况（有息资产负债率已达36.64%） 建议关注公司应收账款状况（应收账款/利润已达144.48%） 以上内容为证券之星据公开信息整理，由AI算法生成（网信算备3101043457103012 ...

Core Viewpoint - Guangzhou Port Company Limited reported a slight increase in revenue but a decline in net profit for the first half of 2025, reflecting challenges in the port industry amidst economic pressures and competition [2][3]. Company Overview and Financial Indicators - The company achieved an operating revenue of approximately 6.91 billion RMB, a 1.39% increase compared to the same period last year [2][11]. - Total profit decreased by 12.11% to approximately 852.96 million RMB, while net profit attributable to shareholders fell by 9.12% to about 551.73 million RMB [2][11]. - The net cash flow from operating activities increased by 19.29% to approximately 1.92 billion RMB [2][11]. - Total assets rose by 2.20% to approximately 53.62 billion RMB, and net assets attributable to shareholders increased by 0.67% to about 21.03 billion RMB [2][11]. Industry and Business Operations - The port industry showed resilience with a national cargo throughput growth of 4.0% in the first half of 2025, and container throughput increased by 6.9% [3][4]. - Guangzhou Port completed a cargo throughput of 287 million tons, a 2.9% increase, and container throughput of 13.4 million TEU, a 9.5% increase [3][4]. - The company expanded its foreign trade container routes, adding 7 new routes, with foreign trade containers growing by 21.4% [3][4]. - The company is focusing on enhancing its logistics services and optimizing its cargo structure to adapt to market demands [3][4]. Strategic Developments - The company is advancing key projects, including the Nansha Port Phase V project and the Nansha International General Terminal, which are crucial for future capacity expansion [4][5]. - Efforts are being made to improve operational efficiency and reduce costs through digital transformation and innovation in logistics services [5][6]. - The company is committed to building a green port, implementing various environmental initiatives and enhancing energy efficiency [6][7]. Competitive Position - Guangzhou Port is strategically located in the Guangdong-Hong Kong-Macao Greater Bay Area, providing significant logistical advantages and connectivity to major domestic and international markets [8][9]. - The port has established partnerships with major shipping companies and alliances, enhancing its service network and operational capabilities [9][10]. - The company aims to align with national strategies such as the Belt and Road Initiative and the development of a comprehensive transportation system, positioning itself for sustainable growth [7][8].