cv
Basics
Name | Seunghyun(Joe) Lee |
Label | Industrial Engineering Student |
sehyun.lee@mail.utoronto.ca | |
Phone | (437) 660-9391 |
Url | https://github.com/sehyunlee217 |
Work
-
2025.05 - Present Toronto, Canada
Data Analyst Intern
Kijiji
Working as a data analyst intern at Kijiji, the largest Canadian online classifieds platform.
-
2024.05 - 2024.08 Toronto, Canada
Undergraduate Research Assistant
Safety, Equity, and Design (SED) Lab, University of Toronto
Analyzed usability testing data and collaborated with SickKids Hospital to evaluate machine learning applications and team-based interventions in emergency healthcare settings.
-
2021.06 - 2023.01 Icheon, South Korea
Education
-
2020.09 - 2027.05 Toronto, Canada
Bachelor of Applied Science
University of Toronto
Industrial Engineering
GPA: 3.7/4.0
- Machine Learning
- Operations Research
Awards
- 2024.05
MIE Summer Research Award
University of Toronto
Awarded $7,500 to support undergraduate research on the application of machine learning in patient safety interfaces and healthcare usability.
Skills
Programming Languages | |
Python | |
R | |
Java | |
JavaScript |
Data Tools & Technologies | |
PostgreSQL | |
MongoDB | |
Apache Spark | |
Azure DataBricks |
Projects
- 2024.08 - 2024.11
Modeling and Forecasting Ontario’s Monthly Energy Consumption
Developed dynamic regression models to forecast monthly energy consumption trends in Ontario, achieving a 2% improvement in predictive accuracy over SARIMA baseline.
- Analyzed historical energy and weather data to uncover non-linear seasonal trends.
- Built a scalable pipeline for infrastructure planning and energy optimization.
- 2024.07 - 2024.09
Policy-Driven Birth Rate Analysis in South Korea
Evaluated the impact of maternity policies on South Korea’s fertility rate using multi-linear regression.
- Outperformed baseline models by 10% in predictive accuracy.
- Forecasted a 20% fertility improvement by increasing maternity leave to 84.5% by 2030.
- 2024.05 - 2024.07
Coffee Bean Multi-Classification
Trained a neural network using PyTorch and EfficientNet to classify four levels of coffee bean roasts.
- Achieved 90% test accuracy.
- Deployed live demo via Hugging Face Spaces for open-source access.