Summary
Education
Skills
Internships
Projects
Timeline
Generic

Justin Chen

Richmond Hill,Ontario

Summary

Hard working, ambitious and always eager to learn new technologies/concepts efficiently. Track record of applying and deeply understanding technical concepts in Data Science.

GitHub:

https://github.com/jjustindoesstats

Tableau Public Profile:

https://public.tableau.com/app/profile/justin.chen6879


Education

Bachelor of Science - Mathematics And Statistics

McMaster University
Hamilton, ON
05.2023

Skills

  • Strong background in Math, Stats and Machine Learning
  • Knowledge of LaTeX
  • Proficient in Python
  • Proficient with SQL (MySQL)
  • Proficient with Tableau
  • Excellent presentation skills
  • Working knowledge of the following libraries: scikit-learn , pandas ,numpy, matplotlib , seaborn, Beautiful Soup
  • Experience scrapping data from websites

Internships

Research Assistant-Bank of Canada (September 2023 - Present)

-Working with Economists/Researchers on Banking and Payments research projects

-Implementing data simulation algorithms from scratch using Python in order to better understand consumer and seller behavior

-Cleaning and Analyzing a 26 Million row payment data set using Python and SQL to discover the correlation between repurchasing agreements and payments made between large financial institutions



Projects

Senior Thesis (A+)(Python, LaTeX)

Supervisor:Distinguished Professor, Narayanaswamy Balakrishnan

-Involved reading, learning, and presenting new concepts in statistics as well as implementing data simulation algorithms in python

-Developed a new way to model stochastic data via the 'Weighted Poisson Process'


NBA Playoff Betting Analysis (Python, SQL,Tableau)

-Worked with Sports Strategist to efficiently analyze data and evaluate the risk of certain sports bets 

-Built a function in python that scrapes/collects data from BasketballReference.com 

-Visualized collected data using Tableau, created multiple dashboards demonstrating player performance and potential


DoorDash Arrival time prediction project (Python)

-Cleaned, Processed and feature engineered a 200,000 row data set with categorical and continuous ride share data

-Methods used:K-Means Clustering,PCA, Sequential Neural Network (Adam optimizer), Linear Regression,Random Forest and XG Boost

-Results: fit a boosted tree model that predicted the correct arrival within 1000 seconds of the actual time (measured by root mean squared error)




Timeline

Bachelor of Science - Mathematics And Statistics

McMaster University
Justin Chen