THE RESULT
What the data shows
The largest computed metric is 41.74 for Median baseline; the smallest is 40.4 for Ridge. Metric: mae (Wh MAE).
Forecast origin is one hour before each target interval, assuming the latest lagged interval has finalized. Later test predictions can use already observed earlier actuals.
| model | mae | rmse | r2 | bias |
|---|---|---|---|---|
| Median baseline | 41.74 | 94.46 | -0.1569 | -34.79 |
| Ridge | 40.4 | 78.34 | 0.2044 | 1.574 |
| Extra trees | 41.23 | 76.52 | 0.2408 | 7.269 |
THE METHOD
From source to answer
Chronological regression with clock-time lags at 1, 2 and 24 hours.
The Python source exposes this study’s transformations. The complete project download includes shared preparation and evaluation routines.
EVALUATION
How the result was checked
First 80% of ordered observations train; final 20% test.
Fixed configurations specified before scoring; no tuning on the holdout.
Target and input features
Target: appliances
Inputs: hour, weekday, lag_6, lag_12, lag_144, prior_hour_mean
THE NEXT DECISION
What follows from the finding
Measure reporting latency and test on a later season before using the forecast operationally.
Where the conclusion stops
Measurements come from one home over a limited period. Energy is Wh per recorded 10-minute interval. This is not a representative household sample; tariffs and occupancy labels are unavailable.
Related studies may reuse observations or holdouts. These are historical analyses; associations and backtests do not demonstrate commercial impact. Further model tuning needs new, untouched evaluation data.