Convert event CSV data into quantitative trading signals with time decay.
npx skills add https://github.com/GGwujun/SigmX --skill event-driven-ggwujun
Please help me install this Agent Skill. Skill: event-driven Source: https://github.com/GGwujun/SigmX/tree/main/agent/src/skills/event-driven Command: npx skills add https://github.com/GGwujun/SigmX --skill event-driven-ggwujun
Converts event information from news, announcements, and macro updates into quantitative trading signals by scoring sentiment and integrating with existing technical signals.
Provide the latest event CSV and run the signal engine to produce a combined technical and event trading signal.
High-intent search queries and answers about installing and using this skill.
News sentiment is converted into quantitative trading signals by scoring event information on a -1.0 to 1.0 scale using an LLM, then applying a time decay model to combine these scores with technical signals.
An LLM sentiment scorer works with event-driven trading by processing a standard CSV schema of news and macro updates to generate bounded scores from -1.0 to 1.0, which are then aggregated into final trading signals.
You can use a standard CSV format containing date, event type, score, source, and summary to backtest equity trading signals by running the signal engine to aggregate event data with technical signals.
The best way to combine event data with technical signals for live trading is using a signal engine that applies time decay to event scores and merges them with technical indicators to produce a bounded final signal.
Event-driven signal generation supports macro and insider events by processing earnings, policy, and sentiment updates through a standardized LLM prompt and decaying signal model for backtests and live equity trading.
Event-driven signals decay over time because the signal engine applies a time decay model to event scores, ensuring that outdated news sentiment gradually reduces its impact on the combined technical and event trading signal.
ebrahim-saniConvert news into time-decayed event signals for algorithmic trading.
Liangwei-zhangScore sentiment-driven news and macro events into CSV trading signals.
santoosaraujoAnalyze financial news sentiment to generate trading signals with time-decay aggregation.
hxhyyyGenerate sentiment-based trading signals from financial news and macro events.
