# DemandLoom — Demand Forecasting Studio

> Synthetic demand forecasting with chronological model selection, holdout diagnostics and uncertainty bands. Precomputed browser demonstration; not live enterprise forecasting or investment modelling.

- Canonical URL: https://mkgrow.co.business/
- Methodology & Equations: https://mkgrow.co.business/methodology/
- Interactive Browser Runtime: https://mkgrow.co.business/run/
- Author & Root Entity: Mohammad Rezwan Khan, PhD (https://mrkhan.co.technology/#person)
- Ecosystem Directory: https://mklab.co.technology/
- Knowledge Graph JSON-LD: https://mkgrow.co.business/knowledge-graph.jsonld

## Governing Mathematical Formulation & Units
- Formula: `MAE = (1/H) Σ |y_t − ŷ_t|; RMSE = sqrt((1/H) Σ (y_t − ŷ_t)²); WAPE (%) = (Σ |y_t − ŷ_t| / Σ |y_t|) × 100; Scenario Projection ŷ_scen(t) = ŷ_selected(t) × (1 + s/100)`
- Units: Demand in hourly synthetic units; horizon H in hours (12 h to 48 h); scenario adjustment s in percent (%); error metrics in demand units and WAPE in %.

## Reproducible Worked Example
Case 1 (56-day synthetic history, seed=17, H=12 h horizon, -15% demand scenario): Rolling 3-fold validation selects Seasonal Persistence (selection MAE = 28.47) over Moving Average and Linear Trend. On the 12-hour holdout window, MAE = 25.10 units, RMSE = 33.82 units, Bias = -16.54 units, and WAPE = 1.97%.