Urban Gentrification & Socio-Economic Displacement Risk Engine
Score Bhubaneswar wards for displacement risk using census, satellite and property data.
About this internship
Data Acquisition & Spatial Wrangling (GIS & Open Data)
- Demographic Scraping: Extracting hyper-local neighborhood data (such as census tracts or ward-level data) focusing on vulnerability indicators: median household income, percentage of renters versus homeowners, educational attainment, and minority or migrant population shares.
- Real Estate Market Tracking: Scraping or API-integrating housing market data to track rapid surges in median property prices, residential rent spikes, and commercial lease rates over a 3-to-5-year timeline.
- Built-Environment Mapping: Geospatially mapping "gentrification triggers" using GIS tools (QGIS, ArcGIS, or Python's
geopandas). This includes plotting new transit corridors (e.g., Metro lines), tech parks, high-end retail developments, and changes in zoning laws.
Quantitative Modeling & Risk Indexing
- Metric Standardisation: Normalizing highly diverse datasets (e.g., combining a 40% rent increase with a low-income demographic score) into standard metrics using statistical methods like Z-scores or Min-Max scaling.
- Displacement Engine Logic: Programming the core logic flags of the "Risk Engine" in Excel. They will write rules to classify neighborhoods into risk tiers. For example:
- Tier 1 (High Risk): Low-income, high-renter demographic directly adjacent to a newly announced corporate hub or rapid transit station experiencing a >20% rent spike.
- Historical Backtesting: Running historical data through the engine to see if it accurately predicts neighborhoods that have already undergone gentrification over the last decade.
Dashboard Engineering & Frontend Mockups
- Interactive Heatmapping: Developing interactive maps using libraries like Leaflet, Mapbox, or Streamlit to allow urban planners to filter by risk level, demographic density, and property value inflation.
- Time-Series Visualisation: Building UI elements (graphs/charts) that display the trajectory of a neighborhood's displacement risk over a projected timeline.
Policy & Qualitative Research
- Impact Assessments: Writing short case studies on vulnerable communities within the target city to provide qualitative context to the raw numbers generated by the engine.
- Mitigation Research: Benchmarking anti-displacement strategies from other global cities (such as inclusionary zoning, rent stabilization frameworks, or community land trusts) to include as policy recommendations inside the engine's output reports.