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.

Blended confluence score

What it is

Blended confluence score — registry key screener_blended_score.

Weighted average of score_norm values across all archetypes that fired for a ticker. Weights come from screener_config.json rank.confluence_weights (default equal 1.0 per archetype). Range [0, 1]. Secondary sort signal for the screener board (sort 2: blended_score desc after confluence_count). Computed by rank.py rank_candidates().

Source

Source module: screener
Data source: computed

Derived metric — produced inside the platform (app/sources/screener.py or equivalent) rather than fetched as a raw upstream value. See the How it's computed section below for the formula.

How it’s computed

sum(weight_i * score_norm_i) / sum(weight_i) for each archetype i that fired for this ticker. Weights from screener_config.json rank.confluence_weights. None when all score_norms are None.

Where it surfaces

• API field: screener.candidates.blended_score on GET /api/v1/signals/latest

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: daily