I'm an Astrophysics Research Scientist excited to impact the world using data.

🔭 Astrophysics research scientist with 8+ YOE in quantitative data-driven research and analysis
📚 PhD in Astronomy & Astrophysics + HBSc in Astronomy & Physics from the University of Toronto
📝 Published several technical papers in high-impact research journals
👥 Mentored a student on a year-long data project through to publication
💬 Taught 500+ technical and non-technical students over 17 classes, including on the use of Python
🌱 Currently learning supervised ML (logistic regression, KNN, Random Forest, forecasting)
🧵 Fun fact: I cross-stitch realistic astronomy observations on Etsy

Languages: Python (NumPy, Pandas, Matplotlib, Seaborn, Scikit-Learn, SciPy), SQL (BigQuery, MySQL)
Tools: Tableau, Git/GitHub, Jupyter Notebook, MS Office Suite (Excel, PowerPoint, Word)
Techniques: EDA, Statistical analysis, Data pipelines, ML, Fourier Analysis, Documentation, Quantitative Research, Technical writing, Data visualization

Email me at [email protected]
Connect with me on LinkedIn at linkedin.com/astrosica

• Credit Card Application Prediction: Developed a prediction model that determines whether a credit card application will be approved or denied using Logistic Regression, KNN, and Random Forest models in Python.

• Insurance Analysis: Developed an interactive Tableau dashboard to report and analyze 70K insurance claims, providing actionable insights to guide future marketing and budget decisions as a PowerPoint presentation.
• Marketing Analysis: Performed exploratory analysis and data validation of 100K sales records for a sample e-commerce company using Excel and SQL (Google BigQuery). Developed an interactive Tableau dashboard to report sales and marketing metrics.
• TTC Delay Analysis: Performed exploratory analysis and data cleaning of 40K subway delays for 2022-2023 using SQL and Tableau to investigate performance metrics, YoY KPIs, and performance strategies.

• Predicting loan repayments: Predicted whether a lender will repay their loan using decision trees and random forest.
• Classifying anonymized data: Classified anonymized data into two target classes using k-nearest neighbours (KNN).
• Predicting ad clicks: Predicted whether someone will click on an ad using logistic regression.