Paper: arXiv 2502.01574

Abstract

This project introduces an end-to-end trading system that leverages Large Language Models (LLMs) for real-time market sentiment analysis. By synthesizing data from financial news and social media, the system integrates sentiment-driven insights with technical indicators to generate actionable trading signals. FinGPT serves as the primary model for sentiment analysis, ensuring domain-specific accuracy, while Kubernetes is used for scalable and efficient deployment.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper relies on standard ML techniques and NLP (no advanced math/derivations), but provides a detailed implementation roadmap, uses real-time APIs, and mentions specific performance metrics like Sharpe Ratio and Win Ratio, indicating a data-heavy, backtest-ready approach.

Research Flowchart

  flowchart TD
  A["Research Goal: End-to-End LLM Trading System"] --> B["Data Acquisition & Preprocessing"]
  B --> C["Computational Process: FinGPT Sentiment Analysis"]
  C --> D["Signal Generation: Sentiment + Technical Indicators"]
  D --> E["Kubernetes Deployment for Real-time Execution"]
  E --> F["Key Outcomes: Actionable Trading Signals & Scalable System"]