Group 1 - The core point of the article is that Ningbo Gaofa (603788.SH) plans to establish a wholly-owned subsidiary in Yiwu to deepen its domestic market presence based on customer demand and business development needs [1] - The total planned investment for the project is not to exceed 100 million yuan, which will include fixed asset investment, research and development expenses, and working capital [1]

宁波高发（603788）(603788.SH)发布公告，公司为深耕国内市场，根据客户需求及公司业务发展需 要，拟以自有资金投资设立义乌全资子公司，名称：义乌高发汽车控制系统有限公司。该项目计划投资 总额不超过1亿元，包括但不限于固定资产投资、研发投入和营运资金投入。 ...

宁波高发公告称，公司为深耕国内市场，拟以自有资金不超1亿元投资设立义乌高发汽车控制系统有限 公司，暂定注册资本1000万元。2026年2月10日，公司第五届董事会第十八次会议已审议通过该议案， 本次投资无需提交股东会审议，不构成关联交易及重大资产重组。子公司法定代表人等为钱国年，财务 负责人为陈辉。项目可能面临不确定因素，投资收益存不确定性。 ...

格隆汇2月10日丨宁波高发(603788.SH)公布，公司为深耕国内市场，根据客户需求及公司业务发展需 要，拟以自有资金投资设立义乌全资子公司。该项目计划投资总额不超过人民币10,000万元，包括但不 限于固定资产投资、研发投入和营运资金投入。董事会授权公司董事长指定工作人员签署及实施本次对 外投资相关事宜，包括但不限于签署投资协议、办理全资子公司注册等相关事宜。 ...

Group 1 - The stock price of Ningbo Gaofa (603788) closed at 16.37 yuan on February 5, 2026, with a decrease of 0.3% and a turnover rate of 0.78% [1] - The trading volume was 17,500 shares, with a total transaction amount of 28.626 million yuan [1] - On February 5, the net inflow of main funds was 759,200 yuan, accounting for 2.65% of the total transaction amount [2] Group 2 - Ningbo Gaofa has used idle self-owned funds to roll over and purchase financial products totaling 220 million yuan, including treasury reverse repos, structured deposits, and securities company income certificates [1][2] - The financial products are managed by various financial institutions, including Guosen Securities, SPD Bank, China Merchants Bank, and others [1] - The investment period ranges from short-term to within one year, with the funds sourced from idle self-owned funds and some from previously matured financial products [1]

Core Viewpoint - The company is utilizing idle funds for structured deposits and purchasing financial products to enhance capital efficiency and returns, while ensuring normal operational liquidity is maintained [2][3]. Group 1: Basic Information on Entrusted Wealth Management - The company plans to use up to RMB 500 million of idle self-owned funds for structured deposits and financial products from banks, securities firms, or trust companies [2]. - The decision was approved by the company's board and shareholders, with details disclosed in specific announcements [2]. Group 2: Progress and Risk Situation of Entrusted Wealth Management - From November 7, 2025, to the date of the announcement, the company has invested RMB 220 million in various financial products, including government bond reverse repos and products from several banks and securities firms [2][3]. Group 3: Impact on the Company and Risk Control Measures - The investment of idle funds is conducted without affecting the company's main business, financial status, or cash flow, thereby improving the efficiency and returns of idle funds [2]. - The company has established a risk control framework for purchasing financial products, ensuring effective execution and compliance with approval processes [3]. - The finance department will monitor the investment and take necessary actions if risks to fund safety are identified, with oversight from independent directors and the supervisory board [3][4].

Core Viewpoint - Ningbo Gaofa (603788) reported a closing price of 16.42 yuan on February 4, 2026, with a 1.3% increase and a trading volume of 21,500 shares, amounting to a total transaction value of 35.1583 million yuan [1]. Trading Information Summary - On February 4, the main funds experienced a net outflow of 2.3263 million yuan, accounting for 6.62% of the total transaction value [2]. - Retail investors saw a net inflow of 758,600 yuan, representing 2.16% of the total transaction value [1]. Company Announcement Summary - Ningbo Gaofa has utilized idle self-owned funds to roll over and purchase financial products totaling 220 million yuan, which includes treasury reverse repos, structured deposits, and securities company income certificates [1][2]. - The financial institutions involved as trustees include Guosen Securities, SPD Bank, China Merchants Bank, Bank of Communications, and Ningbo Bank [1]. - The investment period ranges from short-term to within one year, with the funds sourced from idle self-owned capital and some from previously matured financial products [1].

证券代码：603788 证券简称：宁波高发 公告编号：2026-001 宁波高发汽车控制系统股份有限公司 关于使用闲置自有资金委托理财的进展公告 | 产品名称 | 招商银行点金系列看涨两层区间 90 天结构性存款（产品代码： | | --- | --- | | | NNB01895） | | 受托方名称 | 招商银行股份有限公司 | | 购买金额 | 万元 4,000 | | 产品期限 | 2025/12/30-2026/03/30 | 重要内容提示： 基本情况 | 产品名称 | 国债逆回购（204007-GC007） | | --- | --- | | 受托方名称 | 国信证券股份有限公司 | | 购买金额 | 3,000 万元 | | 产品期限 | 2025/12/26-2026/01/05 | | 产品名称 | 国信证券股份有限公司收益凭证【稳健增益 期】 9 | | --- | --- | | 受托方名称 | 国信证券股份有限公司 | | 购买金额 | 万元 1,000 | | 产品期限 | 2026/1/6-2026/11/26 | | 产品名称 | 国信证券股份有限公司收益凭证【鑫安看涨 23 期 ...

Group 1 - Ningbo Gaofa Automotive Control System Co., Ltd. has invested 1 million RMB to establish Gaofa International Investment (Hainan) Co., Ltd., holding 100% of the shares [1] - Gaofa International Investment (Hainan) Co., Ltd. was established on August 8, 2025, with a registered capital of 1 million RMB and is located in Sanya City [1] - The company is involved in the business services industry, with permitted business activities including technology import and export, goods import and export, and general manufacturing of automotive parts [1] Group 2 - The legal representative of Gaofa International Investment (Hainan) Co., Ltd. is Qian Gaofa [1] - The company’s general business activities include manufacturing, remanufacturing, and research and development of automotive parts, as well as investment activities using its own funds [1] - The company is required to conduct its general business activities in accordance with the law and is publicly listed through the National Enterprise Credit Information Publicity System (Hainan) [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]