ABOUT ME: Accomplished data scientist with a strong track record of extracting actionable insights from data. Adept at leveraging advanced machine learning techniques and big data technologies to build efficient, scalable solutions. Skilled in communicating sophisticated technical concepts to both technical and non-technical stakeholders, fostering informed decision-making. Passionate about continuous learning and applying innovative approaches to solve real-world problems.
Fung Excellence Scholarship
Highest Honors
• Developed robust predictive models ussing traditional and alterna- tive data for credit-risk assessment, supporting the underwriting of millions of dollars of loans in the specialty finance industry.
• Utilized and worked extensively with big-data and cloud technolo- gies such as GCP’s Vertex AI, Dataproc, BigQuery and Apache Spark to securely and efficiently analyze millions of records of consumer data.
• Communicated complex technical concepts and analytical findings effectively to stakeholders with varying levels of technical expertise, facilitating informed decision-making processes.
• Created data pipelines using Apache AirFlow to efficiently transform and load terabytes of consumer credit data.
• Conducted thorough data preprocessing and feature engineering to optimize model performance and enhance predictive accuracy.
• Designed compelling data visualizations using tools like Matplotlib, Seaborn, and ggplot2 to effectively communicate complex insights to stakeholders.
• Conducted novel economic research in the areas of finance and industrial organization.
• Collaborated with economists to produce statistical analyses of economic data used in banking regulation, monetary policy, and academic research.
• Provided technical expertise to assist economists with the gather- ing, cleansing, engineering and analysis of data, including natural language processing, web scraping, and machine learning.
• Developed ETL pipeline in Python, R, and Bash to update and main- tain MySQL database and data dashboard.
• Created data visualizations in R and Python for use in reports to the Congress and Board of Governors.