LLMs can become useful analysis assistants when they have structured data and real‑time market context, meaning they have enough relevant information for the task.
Getting specific indicators, news, and candles into an LLM is difficult, even with search tools integrated. You still need structured inputs, the right context, and a way to ensure everything the model receives is accurate and relevant.
For this reason, I built a system that prepares and delivers all required market data to LLMs in a clean, structured, and consistent format.
I'm excited to share my , a research‑driven system for developing and evaluating crypto signals with LLMs, quantitative models, and historical data.
• including candles, order‑book metrics, recent trades, and technical indicators
• ‑ for crypto news, whale activity, policy, macro events, exchange updates, and whale alerts
• for choosing free or paid models from OpenAI, Google, Anthropic, Mistral, and others
• and repeated iterations for consistency checks
• mapped to models and iteration cycles
• for additional market evidence, with selected model families running in parallel
• before live signal analysis
• including win rate, returns, drawdown, profit factor, buy‑and‑hold comparison, outperformance, LLM agreement, direction accuracy, confidence calibration, and cost
• for qualifying signals
• and prompt files for reproducible experiments
• ‑ signals are saved automatically, and the system later checks real future candles to label each one, giving you clean ground‑truth data for future agent training
• for live signal analysis, testing, configurations, prompts, settings, logs, and ML data
The platform is designed for continuous research, experimentation, and strategy improvement. It generates signals and alerts but does not place exchange orders automatically.
Project: https://github.com/haidarali0/Trading-Signal-Server
My Linkedin: https://www.linkedin.com/in/haidar-s-ali-58030321b/
