hdb-price-predictor
In-browser Singapore property valuation engine for HDB flats and private condominiums powered by dual XGBoost models (< 1ms JS inference). Features interactive
What is hdb-price-predictor?
In-browser Singapore property valuation engine for HDB flats and private condominiums powered by dual XGBoost models (< 1ms JS inference). Features interactive transaction maps and two prediction modes: historical comparable valuation and index-adjusted forward projection.
Overview of hdb-price-predictor
What it is
An in-browser AI engine and automated machine learning pipeline for estimating Singapore Housing & Development Board (HDB) resale flat prices. It is powered by client-side XGBoost tree traversal with sub-millisecond latency, runs entirely inside the user's browser with zero server cold starts, zero hosting costs, and offline capability. The application also provides valuation for private non-landed condominiums using a second independently trained XGBoost model. The live deployment is hosted on GitHub Pages.
Key features
- Client-side machine learning: direct in-browser evaluation of 600 XGBoost decision trees in pure JavaScript (~0.2ms), real-time reactive price recalculation, zero server dependencies, offline-capable.
- Instant postal code auto-fill: automatically retrieves town and lease commencement year from a catalog of 9,818 Singapore postal codes.
- Integrated transaction maps: embedded Leaflet/OpenStreetMap maps showing up to the last 50 real resale transactions for both HDB postal codes and private non-landed developments, without external API keys.
- Valuation range and breakdown: provides an estimated resale price with an indicative valuation range derived from the model's forward-looking validation MAPE, plus Price per Sqm, Price per Sqft, and Remaining Lease at expected sale date.
- Modern responsive UI: dark and light mode options with state persistence, glassmorphic card design optimized for mobile and desktop.
- Automated Python ETL and training pipeline: standalone pipeline that fetches live transactions from Data.gov.sg API and retrains the model in seconds.
Use cases
- Estimating the resale price of an HDB flat or private condominium in Singapore using historical comparable valuation (within the training window) or index-adjusted forward projection (beyond the training cutoff).
- Exploring recent transaction data on a map for a specific block or development.
- Running the entire valuation engine offline or in environments without server infrastructure.
Getting started
See the repository README for installation and usage instructions.
License and pricing
The license is not stated in the repository metadata. The project is listed as open source.
Based on the project's public README and repository metadata.