An LLM-based system that interprets complex business events from financial news and generates actionable trading signals. Goes beyond traditional sentiment analysis by understanding event implications (partnerships, mergers, product launches) and their market impact.
| android | ||
| ios | ||
| lib | ||
| linux | ||
| macos | ||
| test | ||
| web | ||
| windows | ||
| .gitignore | ||
| .metadata | ||
| analysis_options.yaml | ||
| pubspec.lock | ||
| pubspec.yaml | ||
| README.md | ||
Augor
Drilling beneath surface sentiment to extract trading signals from financial news.
What is this?
Augor uses Large Language Models to interpret business events and generate trading signals. Instead of just counting positive/negative words, it understands what events mean for markets.
Traditional sentiment analysis: "This news mentions 'partnership' → positive"
Augor: "This partnership expands market access but dilutes margins → mixed signal"
Why?
Traditional NLP methods are limited:
- Can't understand context or nuance
- Miss complex implications of business events
- Struggle with negation and sarcasm
LLMs can reason about why news matters, not just classify it as positive/negative.
What it does
- Aggregates news from multiple sources
- Interprets business events (mergers, partnerships, product launches)
- Generates trading signals based on reasoned analysis
- Backtests performance against traditional approaches
Author
Benjamin Watt
Supervisor: Panagiotis Kanellopoulos
University of Essex