stonks-oracle/infra/migrations/035_model_validation.sql

-- Migration 035: Model Validation, Calibration, and Signal Quality
-- Creates tables for prediction snapshots, outcomes, evidence links, and metric snapshots
-- Plus views for prediction performance and source performance analysis

-- ============================================================================
-- Table: prediction_snapshots
-- Immutable snapshot of a prediction at generation time
-- ============================================================================
CREATE TABLE IF NOT EXISTS prediction_snapshots (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    generated_at TIMESTAMPTZ NOT NULL,
    ticker VARCHAR(20) NOT NULL,
    "window" VARCHAR(20) NOT NULL,
    horizon VARCHAR(50) NOT NULL,
    direction VARCHAR(20) NOT NULL,
    action VARCHAR(20) NOT NULL,
    mode VARCHAR(50) NOT NULL,
    strength FLOAT NOT NULL,
    confidence FLOAT NOT NULL,
    contradiction FLOAT NOT NULL DEFAULT 0.0,
    p_bull FLOAT,
    p_bear FLOAT,
    score_company FLOAT NOT NULL DEFAULT 0.0,
    score_macro FLOAT NOT NULL DEFAULT 0.0,
    score_competitive FLOAT NOT NULL DEFAULT 0.0,
    evidence_count INTEGER NOT NULL DEFAULT 0,
    unique_source_count INTEGER NOT NULL DEFAULT 0,
    duplicate_evidence_count INTEGER NOT NULL DEFAULT 0,
    price_at_prediction FLOAT,
    spy_price_at_prediction FLOAT,
    sector_etf_price_at_prediction FLOAT,
    metadata JSONB DEFAULT '{}',
    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);

CREATE INDEX IF NOT EXISTS idx_pred_snap_ticker ON prediction_snapshots(ticker);
CREATE INDEX IF NOT EXISTS idx_pred_snap_generated ON prediction_snapshots(generated_at);
CREATE INDEX IF NOT EXISTS idx_pred_snap_horizon ON prediction_snapshots(horizon);

-- ============================================================================
-- Table: prediction_outcomes
-- Realized outcome for a prediction at a specific horizon
-- ============================================================================
CREATE TABLE IF NOT EXISTS prediction_outcomes (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    prediction_id UUID NOT NULL REFERENCES prediction_snapshots(id),
    evaluated_at TIMESTAMPTZ NOT NULL,
    horizon VARCHAR(20) NOT NULL,
    future_price FLOAT,
    future_return FLOAT,
    spy_future_price FLOAT,
    spy_return FLOAT,
    sector_etf_future_price FLOAT,
    sector_etf_return FLOAT,
    excess_return_vs_spy FLOAT,
    excess_return_vs_sector FLOAT,
    direction_correct BOOLEAN,
    profitable BOOLEAN,
    metadata JSONB DEFAULT '{}',
    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);

CREATE INDEX IF NOT EXISTS idx_pred_out_prediction ON prediction_outcomes(prediction_id);
CREATE INDEX IF NOT EXISTS idx_pred_out_horizon ON prediction_outcomes(horizon);
CREATE INDEX IF NOT EXISTS idx_pred_out_evaluated ON prediction_outcomes(evaluated_at);

-- ============================================================================
-- Table: signal_evidence_links
-- Link between a prediction and a contributing evidence document
-- ============================================================================
CREATE TABLE IF NOT EXISTS signal_evidence_links (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    prediction_id UUID NOT NULL REFERENCES prediction_snapshots(id),
    document_id VARCHAR(200),
    signal_id VARCHAR(200),
    ticker VARCHAR(20),
    source VARCHAR(200),
    source_type VARCHAR(50),
    catalyst_type VARCHAR(50),
    sentiment VARCHAR(20),
    impact FLOAT,
    extraction_confidence FLOAT,
    weight FLOAT,
    is_duplicate BOOLEAN NOT NULL DEFAULT FALSE,
    canonical_evidence_key VARCHAR(64),
    contribution_score FLOAT,
    metadata JSONB DEFAULT '{}',
    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);

CREATE INDEX IF NOT EXISTS idx_sig_ev_prediction ON signal_evidence_links(prediction_id);
CREATE INDEX IF NOT EXISTS idx_sig_ev_document ON signal_evidence_links(document_id);
CREATE INDEX IF NOT EXISTS idx_sig_ev_ticker ON signal_evidence_links(ticker);

-- ============================================================================
-- Table: model_metric_snapshots
-- Aggregate model quality metrics for a lookback/horizon combination
-- ============================================================================
CREATE TABLE IF NOT EXISTS model_metric_snapshots (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    generated_at TIMESTAMPTZ NOT NULL,
    lookback_window VARCHAR(20) NOT NULL,
    horizon VARCHAR(20) NOT NULL,
    prediction_count INTEGER NOT NULL DEFAULT 0,
    win_rate FLOAT,
    directional_accuracy FLOAT,
    information_coefficient FLOAT,
    rank_information_coefficient FLOAT,
    avg_return FLOAT,
    avg_excess_return_vs_spy FLOAT,
    avg_excess_return_vs_sector FLOAT,
    calibration_error FLOAT,
    brier_score FLOAT,
    buy_win_rate FLOAT,
    sell_win_rate FLOAT,
    hold_win_rate FLOAT,
    metadata JSONB DEFAULT '{}',
    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);

CREATE INDEX IF NOT EXISTS idx_model_snap_generated ON model_metric_snapshots(generated_at);
CREATE INDEX IF NOT EXISTS idx_model_snap_lookback ON model_metric_snapshots(lookback_window);
CREATE INDEX IF NOT EXISTS idx_model_snap_horizon ON model_metric_snapshots(horizon);

-- ============================================================================
-- View: v_prediction_performance
-- Joins prediction snapshots with outcomes for flat analysis
-- ============================================================================
CREATE OR REPLACE VIEW v_prediction_performance AS
SELECT
    ps.ticker,
    ps.direction,
    ps.action,
    ps.confidence,
    ps.strength,
    ps.contradiction,
    ps.p_bull,
    ps.score_company,
    ps.score_macro,
    ps.score_competitive,
    ps.evidence_count,
    ps.unique_source_count,
    ps.duplicate_evidence_count,
    ps.price_at_prediction,
    po.future_return,
    po.excess_return_vs_spy,
    po.excess_return_vs_sector,
    po.direction_correct,
    po.profitable,
    po.horizon,
    ps.generated_at,
    po.evaluated_at
FROM prediction_snapshots ps
JOIN prediction_outcomes po ON po.prediction_id = ps.id;

-- ============================================================================
-- View: v_source_performance
-- Joins evidence links with snapshots and outcomes for source attribution
-- ============================================================================
CREATE OR REPLACE VIEW v_source_performance AS
SELECT
    sel.source,
    sel.source_type,
    sel.catalyst_type,
    sel.sentiment,
    sel.weight,
    sel.contribution_score,
    sel.is_duplicate,
    po.direction_correct,
    po.future_return,
    po.excess_return_vs_spy,
    po.horizon,
    ps.generated_at
FROM signal_evidence_links sel
JOIN prediction_snapshots ps ON ps.id = sel.prediction_id
JOIN prediction_outcomes po ON po.prediction_id = sel.prediction_id;