event-driven

To generate trading signals, this skill uses an LLM to convert news and macro events into a standardized -1.0 to 1.0 impact score. It then applies weighted aggregation and exponential time decay to combine these event-driven signals with technical indicators.

Sentiment analysis for quantitative trading works by standardizing qualitative market information like policy updates into numerical scores. The engine uses time-decay logic to aggregate these sentiment-based signals with technical indicators for multi-factor decision making within a point-in-time safe framework.

Yes, this skill requires pandas and numpy for signal processing and data manipulation within a point-in-time safe framework. They handle the weighted aggregation and exponential time decay logic needed to combine sentiment with technical indicators.

The best way to combine event-driven sentiment with technical indicators is through weighted aggregation using exponential time decay. This standardizes qualitative news into a -1.0 to 1.0 score and merges it with technical data for multi-factor decision making.

You can adjust your trading bias by feeding recent central bank policy announcements and earnings reports into the signal engine. The LLM analyzes these macro events to generate a standardized impact score that automatically shifts your trading bias for a specific asset.