← Back to Portfolio

04 — Backtesting & Financial Valuation

Walk-forward backtesting across multiple base periods with confusion matrices, alert calendars, and financial valuation for a hypothetical 10 MW Class A customer.

backtesting walk-forward financial-analysis global-adjustment
Pythonpandasmatplotlibseabornnumpy

Key Findings

  • Walk-forward validation across 5 base periods demonstrates consistent peak detection performance
  • RED alert precision and recall trade-off calibrated to minimize missed peaks (the costlier error)
  • Model-guided curtailment outperforms naive temperature heuristic by reducing false alarm days

Notebook