Trent TurnerSeasonal Demand Modeling
Identifying the recurring annual demand curve
Read the studyWork / Demand Analytics
Demand Analytics
How can a seasonal business estimate expected weekly customer demand when the annual pattern is predictable, but the absolute demand level and rate of change vary from year to year?
One forecasting problem, seven connected studies. I established simple benchmarks, tested candidate signals, rejected unnecessary complexity, and froze the selected architecture before holdout evaluation.
Flagship integration study · Provisionally validated
Integrated Adaptive Demand Forecast
Recurring seasonality. Current demand level. Local momentum.
19.2%Lower 2025 holdout MAE vs. recent 4-week benchmark
12.7%Lower 2025 holdout RMSE vs. recent 4-week benchmark
The validation sequence
Earn complexity through evidence.
- 2023–2024 development
- Rolling-origin model selection
- Model and score scale frozen
- Untouched 2025 holdout
- 2026 calendar-alignment sensitivity check
Seasonality, adaptive level, and local momentum became model components. Weather and economics were tested but not retained: they did not add sufficient forward-forecast value after the adaptive seasonal structure was modeled correctly.
Seven studies / One system
Environmental Demand Signals
Testing whether weather adds predictive value beyond seasonality
Read the studyAdaptive Demand Level
Measuring whether the current year is running above or below seasonal expectations
Read the studyLocal Demand Momentum
Testing whether recent demand improves forecasts beyond annual seasonality
Read the studyEconomic Demand Signals
Testing macroeconomic signals under forecast-safe constraints
Read the studyIntegrated Adaptive Demand Forecast
Combining seasonality and recent demand signals into an out-of-sample weekly forecasting system
Read the studyDemand Score & Decision Support
Translating predicted demand into an interpretable 0–100 decision layer
Read the study