v1.6.2 - Extended Model Options & Smoothing Control for Signals Endpoint

The signals endpoint now supports eight additional model types — including a latest alias, non risk managed forecasts for both v1 and v2, technical forecasts, as well as individual & aggregated sentiment variants — and exposes a configurable smoothing parameter, giving you finer control over signal stability versus responsiveness.

Added

• Extended model options for GET /signals - The model_name parameter now accepts eight additional values alongside the existing v1 and v2:

  • latest - Alias for the latest available model (currently v2)
  • v1_raw - Forecast signal using the v1 model without additional risk management logic
  • v2_raw - Forecast signal using the v2 model without additional risk management logic
  • sentiment - Aggregated sentiment signal combining fundamental, sector, and macroeconomic inputs
  • technical - Signal based on technical indicators
  • fundamental_sentiment - Signals derived from fundamental sentiment analysis
  • sector_sentiment - Signals derived from sector-level sentiment analysis
  • macroeconomic_sentiment - Signals derived from macroeconomic sentiment analysis

• Smoothing parameter for GET /signals - New smoothing_parameter query parameter (integer, default 2, minimum 1, maximum 48) controls how many consecutive hourly periods a signal must persist before being accepted. Higher values produce more stable but slower-reacting signals; a value of 1 returns the raw latest signal with no smoothing applied.

• Signals model taxonomy endpoint - New GET /signals/models endpoint returns the full list of available signal models with their id, name, and description. Use the id as the model_name parameter when calling GET /signals.