What mathematical model and units does DemandLoom Studio use?

DemandLoom Studio applies 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 %.

What are the operational boundaries and limitations of DemandLoom Studio?

Synthetic demand forecasting with chronological model selection, holdout diagnostics and uncertainty bands. Precomputed browser demonstration; not live enterprise forecasting or investment modelling. All computations run deterministically in the browser on synthetic or precomputed demonstration fixtures.

TECHNICAL METHODOLOGY & VERIFICATION SPECIFICATION

DemandLoom Studio: Mathematical Model, Units & Reproducible Benchmarks

Q: How can I reproduce the benchmark results in DemandLoom Studio?

Open the interactive browser workspace at ./run/, select Case 1 to inspect the worked result (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%.), and export the JSON or CSV evidence ledger.

Role & Domain Intent: Demand-led business planning (Synthetic demand forecasting, not investment or financial-growth advice.)

1. GOVERNING FORMULATION

Equations, Variables & Dimensional Rules

Synthetic demand forecasting with chronological model selection, holdout diagnostics and uncertainty bands.

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)

Declared 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 %.

2. REPRODUCIBLE WORKED EXAMPLE

Step-by-Step Numerical Verification

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%.

Verified benchmark cases from the DemandLoom Studio browser edition
Model Candidate	Fold 1 MAE	Fold 2 MAE	Fold 3 MAE	Selection MAE	Holdout MAE (12h)	Holdout RMSE	Holdout WAPE (%)
Seasonal Persistence	31.11	29.29	24.99	28.47	25.10	33.82	1.97%
Trailing Moving Average	42.18	39.85	36.40	39.48	37.90	45.12	2.98%
Damped Linear Trend	35.60	33.14	29.80	32.85	30.45	38.90	2.39%

3. DATA PROVENANCE & OPERATIONAL BOUNDARIES

Validation Status, Scope Exclusions & Disclaimers

Data Status: Synthetic / precomputed browser demonstration fixtures generated deterministically from the project engine.
Operational Limitation: Precomputed browser demonstration; not live enterprise forecasting or investment modelling.
Client-Side Execution: All interactive views, filters, and JSON/CSV exports execute locally in the user's browser with zero external API calls, zero telemetry, and no server-side persistence.
Author & Principal Investigator: Mohammad Rezwan Khan, PhD (Aalborg University · BESS QA/QC & Power Systems Specialist).