Mingyue Chen

Armed with a double major in Statistics and Quantitative Finance, complemented by a minor in Economics, I bring a solid foundation in both fundamental analysis and technical analysis. I enjoy the process of brainstorming and am proactive to turn ideas into reality with a team. 

I have gained valuable professional experience through my internships and project work. During my internship at the Civil Service College Data Office, I achieved a 99% accuracy in the company's data migration pipeline by automating data validation through R code. I also presented solutions to flaws in the data migration process to external collaborators and enhanced the course demand forecasting model's performance by 5% with my team.

At the Bank of China Singapore Branch, I revamped the Account Payable process post-COVID, streamlining operations and processing over 400 supplier invoices using Oracle E-Business Suite. I also played a key role in aiding the department's auditing process, achieving a nearly 100% approval rating from auditors.

In my project work, I demonstrated my skills in stock trading by developing an ensemble model using machine learning techniques to generate buy/sell signals for the SPDR S&P 500 ETF Trust, resulting in a 5% increase in cumulative returns. Additionally, I crafted a saving and loan repayment strategy for migrant workers to enable home ownership within a 20-year timeframe.

Overall, my professional experience showcases my proficiency in data engineering, financial management, and project management, highlighting my ability to drive impactful results through analytical and strategic thinking.

Armed with a double major in Statistics and Quantitative Finance, complemented by a minor in Economics, I bring a solid foundation in both fundamental analysis and technical analysis. I enjoy the process of brainstorming and am proactive to turn ideas into reality with a team. During my exchange program at Singapore Management University, my project team applied Machine Learning in quantitative finance. Collaborating closely with teammates, we developed Ensemble Models using Python to automate stock and fund trading and enhance its cumulative return by 5% than a single trading strategy. Continuing our efforts even to today, we regularly delve into Machine Learning research papers and test the ML models proposed in the paper on our stock/ fund trading algorithms, pursuing more trading return. Recently, we found LSTM outperforms our previous Ensemble models in giving accurate trading signals for SPDR S&P 500 ETF Trust.

To deepen my understanding of the US market and finance landscape, I embarked on exchange program at UC Berkeley this year. Here, I was exposed to the vast credit card market, which differs significantly from that of Singapore. While in the US, individuals typically initiate their credit journey during their university years, in Singapore, it tends to be after entering the workforce. This subtle disparity in timing leads to differences in spending habits and personal wealth management strategies in the two markets.