Experiment Log - FAMILY_HARVEST_TIMING_OPTIMIZATION

Hypothesis

Farmers optimize harvest timing within 2-3 week windows based on weather forecasts and price signals, creating predictable price movements through strategic supply timing.

Data Sources (REAL DATA ONLY)

• Open-Meteo API: 7-14 day weather forecasts, historical weather
• CBS API: Harvest progress data (if available)
• Boerderij API: Weekly potato prices and momentum

Variants

• Variant A: Weather window optimization (forecast-driven timing)
• Variant B: Price signal optimization (momentum and storage economics)
• Variant C: Integrated timing model (weather + price + clustering)

Experimental Runs

Run 1: [Pending]

Date: TBD Variant: TBD Status: Not started

Configuration: - Target horizons: 30-day, 60-day - SESOI: 15% - Seasonal focus: September-November (harvest season) - Baseline models: persistent, seasonal_naive, ar2, historical_mean

Results: - Awaiting implementation

Verdicts

Overall Assessment: PENDING

Awaiting experimental validation.

HE Notes

• Created 2025-08-18
• Builds on FAMILY_WEATHER_ACCUMULATION success (92.4%) and FAMILY_STORAGE_OPTIMIZATION insights
• Industry evidence: Sept 2024 dry window rush → 18% price drop; Oct 2023 delays → 22% spike
• Academic support: Myers et al. (2010) harvest flexibility worth 8-12% of crop value
• Focus on September-November harvest season dynamics
• Uses REAL DATA ONLY from repository interfaces

Decision Log

[To be completed after experiments]