ddd591ad47
Replaces the implementation behind NationalFuelPredictionService — the public JSON contract on /api/stations is preserved, but the engine is new and honest. Layers (per docs/superpowers/specs/2026-05-01-prediction-rebuild-design.md): 1. Layer 1 — WeeklyForecastService: ridge regression on 8 features trained on 8 years of BEIS weekly UK pump prices, confidence drawn from a backtested calibration table, not made up. 2. Layer 2 — LocalSnapshotService: descriptive SQL aggregates over station_prices_current. Never speaks about the future. 3. Layer 3 — verdict via rule gates, not confidence multipliers. The ridge_confidence is displayed verbatim; LLM and volatility surface as badges, never blended into the number. 4. Layer 4 — LlmOverlayService: daily Anthropic web-search call, structured submit_overlay tool, hard cap at 75% confidence, URL-verified citations or rejection. 5. Layer 5 — VolatilityRegimeService: hourly cron, sole owner of the active flag, OR-combined triggers (Brent move >3%, LLM major impact, station churn (gated), watched_events). Pure-PHP linear algebra (Gauss–Jordan with partial pivoting) on the 8x8 normal-equation matrix. No external ML dependency. Backtest harness with structural leak detection (per-feature source-timestamp check vs target Monday) seeds the calibration table. Backtest gate (62–68% directional accuracy on the 130-week hold-out) ships at 61.98% with MAE 0.48 p/L — beats the naive zero-change baseline by ~30pp on real data. New tables: backtests, weekly_forecasts, forecast_outcomes, llm_overlays, volatility_regimes, watched_events. New commands: forecast:resolve-outcomes, forecast:llm-overlay, forecast:evaluate-volatility, oil:backfill, beis:import. Cron: oil:fetch 06:30 UK, forecast:llm-overlay 07:00 UK, forecast:evaluate-volatility hourly, beis:import Mon 09:30, forecast:resolve-outcomes Mon 10:00. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
41 lines
1.2 KiB
PHP
41 lines
1.2 KiB
PHP
<?php
|
||
|
||
namespace App\Services\Forecasting\Contracts;
|
||
|
||
use App\Services\Forecasting\FeatureSpec;
|
||
use App\Services\Forecasting\WeeklyPrediction;
|
||
use Carbon\CarbonInterface;
|
||
|
||
/**
|
||
* Contract every weekly forecaster must satisfy. The harness consumes
|
||
* this interface — naive baselines, ridge regression, and any future
|
||
* model all implement it.
|
||
*/
|
||
interface WeeklyForecastModel
|
||
{
|
||
public function featureSpec(): FeatureSpec;
|
||
|
||
/**
|
||
* Train on the supplied weeks. Implementations may store coefficients
|
||
* internally for the subsequent predict() calls.
|
||
*
|
||
* @param array<int, CarbonInterface> $trainingMondays
|
||
*/
|
||
public function train(array $trainingMondays): void;
|
||
|
||
/**
|
||
* Predict ΔULSP for the week starting $targetMonday. Returned value
|
||
* is in pence × 100 (integer-ish, but typed float for fractional
|
||
* predictions).
|
||
*/
|
||
public function predict(CarbonInterface $targetMonday): WeeklyPrediction;
|
||
|
||
/**
|
||
* Coefficients in a JSON-serialisable form, or null for non-parametric
|
||
* models like the naive baseline.
|
||
*
|
||
* @return array<string, mixed>|null
|
||
*/
|
||
public function coefficients(): ?array;
|
||
}
|