Python & pandas
Data cleaning and analysis pipelines
Data & Analytics
Turning data into decisions
I work from a business question through to cleaned data, analysis, findings, recommendations, and impact — with clear labels when results are measured vs. potential.
How I work
- 1 Business problem
- 2 Data
- 3 Clean
- 4 Analyze
- 5 Findings
- 6 Recommend
- 7 Impact
Skills in context
SQL
Business questions against structured datasets
Jupyter
Exploratory analysis and reproducible notebooks
Dashboards & visualization
Next.js, Recharts, and executive views
Business framing
Questions, findings, and recommendations for stakeholders
Data projects
Data & Analytics
Featured
Canadian Mental Health Data Analytics Platform
Question: How are population-level mental health trends shifting across Canada, and where should public-health attention focus?
What I did: Cleaned StatCan and CIHI exports, built a 27-question SQL layer, shipped a Next.js dashboard, and deployed a FastAPI live prediction service.
Key finding: Provincial and youth-crisis indicators vary sharply by region — patterns are associational, not causal, and require population-level framing.
Business value: Gives policymakers and analysts an explorable view of trends instead of static notebook output, with responsible caveats built in.
Impact (Potential): Supports faster exploration of public mental-health trends; formal measured outcomes depend on stakeholder adoption.
Python · Pandas · SQL · scikit-learn · Next.js · TypeScript
Data & Analytics
GTA Housing Affordability
Question: How affordable is renting in different Greater Toronto Area municipalities when rent is compared to local household income?
My role: Worked with Samriti (project lead) and Rebal on the team pipeline — data extraction, cleaning and joining rent and income datasets, SQL KPI analysis, and dashboard preparation in Microsoft Fabric and Power BI.
Key finding: Affordability varies sharply by municipality; city-level (CSD) data reveals differences that CMA-wide averages hide.
Business value: Helps frame where rent-to-income pressure is highest across GTA cities such as Brampton, Mississauga, Toronto, Oakville, and Markham.
Impact (Potential): Supports municipal-level housing affordability comparisons; formal measured outcomes depend on dashboard completion and stakeholder use.
Python · SQL · Microsoft Fabric · Power BI · CMHC data · Statistics Canada
Data & Analytics
Featured
Bitcoin Price Signal System
Question: Can economic indicator data help flag likely Bitcoin price direction shifts?
What I did: Built a Python pipeline for data collection, analysis, and signal generation with a local API and desktop GUI.
Key finding: Economic data can be structured into repeatable direction signals — experimental, not financial advice.
Business value: Demonstrates end-to-end data ingestion, analysis, and delivery for financial indicator monitoring.
Python · Pandas · Selenium · PyQt6 · APIs
Software Engineering
Data & Analytics
Self French Learning — Platform & Analytics
Question: Where am I making progress in French, and which CEFR skills — reading, writing, listening, or speaking — need more practice?
My role: Built the Next.js platform with structured A1 lessons and interactive exercises, plus a progress dashboard for tracking completion and skill-level practice.
Key finding: Progress is uneven across the four CEFR skills — the dashboard makes those gaps visible instead of leaving them implicit in lesson logs.
Business value: Gives self-directed learners a structured path and a clear view of progress without relying on spreadsheets or guesswork.
Impact (Potential): Supports more intentional French practice for newcomers; measured outcomes depend on continued content growth and learner feedback.
Next.js · Web · Language learning · Interactive exercises · Learning analytics