fingpt_trader
Unverified ML strategy on Crypto by ashioyajotham. BotFinder score 18 out of 100.
A quant trading system platform based on FinGPT, demonstrating new applications of large pre-trained Language Models in quantitative finance.
Source: github
BotFinder analysis pending.
fingpt_trader
FinGPT Trader A quantitative trading system that combines Falcon-7B language model-driven sentiment analysis with technical market analysis to identify cryptocurrency trading opportunities. The system's core innovation is its confidence-weighted sentiment scoring mechanism, which integrates both the sentiment value and the model's confidence level to generate more reliable trading signals. System Overview FinGPT Trader processes financial news and market data in parallel, combining both sources to identify potential trading opportunities. The system uses: - Falcon-7B Model: Fine-tuned for financial sentiment analysis - Confidence-Weighted Scoring: 60% confidence weight, 40% sentiment strength weight - Technical Analysis: Standard technical indicators for market inefficiency detection - RSS-first News Ingestion: Crypto-native publisher RSS feeds, with NewsAPI fallback - Event-Driven Architecture: Asynchronous processing of market events - Risk Management: Basic position tracking and exposure monitoring Current Implementation Status ✅ = Implemented | 🚧 = Partially Implemented | 📅 = Pla
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)