Lag Features, Rolling Windows and Cyclical Hour Encoding: Hourly Load Forecasting Bench
Turn a noisy hourly electricity-load series into the columns a model actually learns from: lag features, rolling-window mean and spread, and a sine/cosine clock. A ridge regression forecasts the next hour and is scored on nine unseen days against persistence and the noise floor, with built-in numerical checks. Desk, window posts, pegs and dial modelled in Blender.
Turn a noisy hourly electricity-load series into the columns a model actually learns from: lag features, rolling-window mean and spread, and a sine/cosine clock. A ridge regression forecasts the next hour and is scored on nine unseen days against persistence and the noise floor, with built-in numerical checks. Desk, window posts, pegs and dial modelled in Blender.
Turn a noisy hourly electricity-load series into the columns a model actually learns from: lag features, rolling-window mean and spread, and a sine/cosine clock. A ridge regression forecasts the next hour and is scored on nine unseen days against persistence and the noise floor, with built-in numerical checks. Desk, window posts, pegs and dial modelled in Blender.
3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install