Experiment Log - FAMILY_EXTREME_WEATHER_INSURANCE

Hypothesis

Extreme weather events trigger insurance payouts that affect farmer planting decisions in the following season, creating predictable potato price movements through altered supply expectations.

Data Sources (REAL DATA ONLY)

• Open-Meteo API: Weather extremes (>99th percentile events)
• BRP API: Annual parcel area changes 2015-2025
• CBS API: Harvest production statistics
• Boerderij API: Weekly potato prices

Variants

• Variant A: Temperature extremes focus (frost/heat as insurance triggers)
• Variant B: Precipitation extremes focus (drought/flood as triggers)
• Variant C: Combined insurance proxy (all extremes integrated)

Experimental Runs

Run 1: [Pending]

Date: TBD Variant: TBD Status: Not started

Configuration: - Target horizons: 30-day, 60-day - SESOI: 15% - 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_EXTREMES (insufficient events) by focusing on insurance behavioral response
• Industry evidence: 2023 Flevoland hailstorm €45M payouts → 15% acreage reduction
• Academic support: Goodwin & Piggott (2001) 0.35 elasticity of planting to insurance
• Uses REAL DATA ONLY from repository interfaces

Decision Log

[To be completed after experiments]