I am a Data Scientist passionate about solving exciting problems, and data visualization.
I hold the Master of Information Management & Systems from UC Berkeley's School of Information for which I studied Machine Learning and Data Visualization. I served as a Data Scientist Researcher at the Othering and Belonging Institute's Equity Metrics team where I used data science to tackle questions of inclusivity including a statewide analysis of the extent and impact of single-family zoning in California.
Also during my master's, I built several Data Science projects involving Machine Learning, Dimensionality Reduction in Python (pandas, scikit-learn), and Spatial Analysis (R, Python (geopandas)); coded Arduino hardware to build a smart scent diffuser; learnt swimming; and studied Punjabi in the Gurmukhi script.
Before that, I was based in Hong Kong between 2018 and 2020 as the Centre for Asian Philanthropy and Society's main data resource and helped produce cross-regional and one-of-a-kind data analysis. From 2015-2018, I worked under eminent economists helping implement a randomized controlled trial in Pakistan (113,000 households spread across two metropoles: Lahore and Faisalabad) aimed at mending the citizen-state social contract.
I am available to discuss collaborations or professional opportunities.
Email  /  CV  /  LinkedIn  /  GitHub
Click on the section below to view examples and read about my Data Science experience.
Tool: R, Python, Geospatial Analysis
Author and Data Lead for a study of the extent and impact of single-family zoning across all of California (481 cities) using spatial (ArcGIS) and data analysis (R) and automation (Python). This project is the Institute’s flagship effort on Zoning Reform. I also helped transition another product’s analysis from Excel to R (currently in use); and wrote testing software in R (testthat) to ensure reliability of a statewide information visualisation tool.
Blogpost and concluding exercise of my 3-month Summer Fellowship at Breakwater Strategy–a boutique strategic communications firm working with household brands–where I provided Data Visualization Leadership. I Updated 50+ client-facing data visualisation slides; templatized my work for reuse and extension; steered a culture of data visualisation by leading 4 bi-weekly company-wide data visualization discussions; and authored a data-viz focused organisational plan to differentiate Breakwater Strategy in the industry. This blogpost (linked) received 3500+ impressions.
Tool: Wireframes, Sketches, PowerBI, Stata
Data Lead for data analysis (Stata) and pioneering presentation style of Doing Good Index 2020, the centre’s flagship research product covering 18 Asian economies, as a scrollytelly platform and interactive dashboard (linked). At large, I helped create a more data-focused org by leading an organization-wide transition from Excel to Stata.