Case Study — Financial Data Intelligence
Batch Disclosure — Price-Moving Catalyst Detection
An AI-powered system that scans ASX and SEC filings for forward-looking disclosures — contracts, M&A, guidance — that move micro-cap prices before the market catches on.
The Challenge
Micro-cap investors were drowning in compliance-length filings. Price-moving catalysts — new contracts, capital raises, earnings guidance — were buried in hundreds of pages of boilerplate, reaching the market late or not at all.
What We Built
- NLP extraction pipeline (spaCy + NLTK) that isolates forward-looking disclosures from boilerplate language
- LangChain + OpenAI classification that grades each disclosure for market-moving potential
- RAG layer that cross-references filings against company history for context-aware scoring
- Fully containerized (Docker) Streamlit dashboard delivering instant, actionable insights
PythonLangChainRAGOpenAIFastAPIDockerspaCyNLTKStreamlit
Results
Screening time per filing
30+ min → under 60 sec
Catalyst detection accuracy
~85% on holdout filings
Manual analyst hours saved weekly
10+ hours
More Work
WikiGen — Autonomous, Bias-Aware Knowledge Synthesis
A multi-agent GraphRAG system that autonomously writes reliable, bias-aware Wikipedia-style articles with verifiable provenance on every claim.
Llama2 QLoRA Healthcare — Medical LLM on One GPU
A fine-tuned LLaMA-2-7B medical assistant trained with QLoRA on a single GPU — production-quality LLM fine-tuning without an expensive compute cluster.
Let's Work Together
Build Something Like This?
This system solved a real problem. We can build something similar for you.