FinSight
Real-time forex intelligence platform fusing live rate APIs with an NLP news aggregation pipeline, stateless zero-PII architecture, and programmatic RBI FEMA rate disclaimers.
Pipeline
Architecture
End-to-end flow, stage by stage.
- 01
Rate APIs
- 02
150+ pairs
- 03
NLP news
- 04
Zero-PII
- 05
React UI
How it works
Built a production data feed for Venus Forex that ingests and normalizes 150+ currency pairs, tracks source timestamps, and applies the firm's buy and sell spread model across 12 active corridors.
Handled financial edge cases explicitly: AED and SAR are derived from USD cross-rates, while JPY is normalized per 100 units to avoid systematic pricing errors.
Added an NLP news pipeline for RSS cleaning and relevance filtering, with timeouts and a curated fallback corpus so the interface continues serving useful market context during source failures.
Kept the system stateless and zero-PII, protected API credentials, rejected stale rate data, and injected indicative-rate disclaimers alongside every quote.
- Zero-PII
- Stateless architecture
- 150+
- Currency pairs normalized
- 12
- Active currency corridors
Stack
More projects
Edge / IoT
On-Device Small Language Model Chatbot
Fully offline SLM chatbot running on-device with no cloud dependency — quantized inference tuned for constrained memory and latency budgets.
Full-Stack
Fresh Start
Award-winning food redistribution platform where restaurants post surplus donations and the community finds them through real-time geolocation search with live availability.