A real-time market-data pipeline for equity research
An automated pipeline that collects and joins financial data for the top 500 Indian equities, feeding forecasting models and backtests used to inform trading strategies.
- Context
- Data scientist engagement
- Role
- Data scientist
- When
- 2025
Results
| Measure | After |
|---|---|
| Equities in the research universe | Top 500 |
| Data acquisition | Real time, automated |
The problem
Research on hundreds of equities depended on data that arrived from many sources at different times. Analysts needed it collected, aligned and ready for modelling without manual work.
What I did
Acquisition and integration
Built and automated a pipeline for real-time acquisition and integration of fundamental, strategic and price data.
Models and backtesting
Developed Python statistical models for price-movement forecasts and systematically backtested strategies across market conditions.
Stack
- Python
- Statistical modelling
- Backtesting