Auto-generated. This article is rebuilt from app/signals/config/signal_definitions.json by scripts/build_signals_kb.py. Edit the registry entry and re-run the script — do not edit this file directly.

EBP Recession Probability

What it is

EBP Recession Probability — registry key ebp_recession_prob.

The Gilchrist-Zakrajšek model’s implied recession probability ingested from the monthly FEDS Notes CSV and persisted on daily_signals for future scoring / matcher use. NOT yet a health-score or alignment component.

Source

Source module: ebp
Data source: back_fillable

Fetched directly from app/sources/ebp.py; see source code for the upstream API call and any provider-specific handling.

How it’s computed

Model-implied probability that the US economy is in (or entering) a recession, derived from the Gilchrist-Zakrajšek EBP framework — a 0-1 fraction. Sourced verbatim from the Fed’s monthly FEDS Notes ebp_csv.csv est_prob column (renamed to ebp_recession_prob for unambiguous reading alongside the platform’s other probability fields), last row. See app/sources/ebp.py.

Where it surfaces

• API field: signals.ebp_recession_prob on GET /api/v1/signals/latest
• Surface: daily_signals row (daily-cadence persistence)
• Surface: /signals/sparklines (UI sparklines)
• Surface: change markers in the rendered report

Health-score / alignment role

Data carrier — no implication, no health-score contribution.

Persisted for downstream consumers (sparklines, base-rate matcher, calibration substrate) but does not classify into BULLISH / NEUTRAL / BEARISH and does not contribute to the 0-100 health score.

Release cadence

• Publishes: monthly
• Approximate time (ET): 08:30

Federal Reserve FEDS-notes monthly Excess Bond Premium CSV (ebp_csv.csv); the est_prob column renamed to ebp_recession_prob, same monthly cadence as EBP, last row is the latest month.

See also

• /kb/api/get-signals-latest — API endpoint that serves this field.