Investment feasibility analysis: led the investment feasibility analysis of four major projects, covering market research, financial analysis and risk assessment, assisted high-level decision-making, and ensured the scientific and sound nature of investment.Portfolio optimization: We proposed portfolio optimization, which is expected to bring a 5% return on investment to the company.Cross-departmental cooperation and process optimization: Led the cross-departmental cooperation… Show more Investment feasibility analysis: led the investment feasibility analysis of four major projects, covering market research, financial analysis and risk assessment, assisted high-level decision-making, and ensured the scientific and sound nature of investment.Portfolio optimization: We proposed portfolio optimization, which is expected to bring a 5% return on investment to the company.Cross-departmental cooperation and process optimization: Led the cross-departmental cooperation, successfully integrated the investment project approval process, improved the efficiency of project approval by 15%, and accelerated the speed of investment execution.Project investment research: Completed the project investment research of about 2 million RMB within one month, providing accurate analysis support for the company's project layout in the field of environmental protection. Show less

Data cleaning and annotation: Responsible for cleaning and annotation of market datasets. In this process, the data accuracy was improved by 20% and the annotation consistency reached 95% by using uniform annotation rules.⚫ Abnormal data processing: Python and SAS are used to automatically identify and process the abnormal data in the market data sets, which reduces the manual correction time and improves the work efficiency by 30%. Furthermore, these data processing error rates were… Show more Data cleaning and annotation: Responsible for cleaning and annotation of market datasets. In this process, the data accuracy was improved by 20% and the annotation consistency reached 95% by using uniform annotation rules.⚫ Abnormal data processing: Python and SAS are used to automatically identify and process the abnormal data in the market data sets, which reduces the manual correction time and improves the work efficiency by 30%. Furthermore, these data processing error rates were reduced by 15% by implementing these automated strategies.⚫ Data set preparation: Accurate data sets are prepared for multiple quantitative analysis and machine learning projects to ensure the accuracy and reliability of the model. These preparations increased the prediction accuracy of the project model by 25%, while reducing the risk of overfitting.⚫ Cross-departmental collaboration: In cross-departmental collaboration, actively participate in project discussions and make suggestions for data processing. These improvements advance the data analysis phase of the project by 15% and enhance the efficiency of collaboration between different departments. Show less