Synthetic case explorer

Forecourt Prism

A clearer view of demand

Inspect short-term volume baselines and the effect of missing observations.

Explore the evidence

Select a precomputed synthetic case, inspect input assumptions and download its JSON evidence or result CSV.

Open Forecourt Prism explorer →

What this edition demonstrates

Weekday-shrunk trailing baseline with backtest errors.

Synthetic volumes and heuristic ranges; not operational demand predictions.

The public website hosts a read-only synthetic projection. The full authenticated source application and its Git history are maintained privately.

All fixtures are fictional. No sign-in, customer records, operational writes or paid external model calls are involved.

Publication notices · Application metadata

Explore the application directory

MATHEMATICAL SPECIFICATION & UNITS

Governing Equations, Inputs, Outputs & Dimensional Conventions

Forecourt Prism executes deterministic client-side calculations in the browser. Every scenario is governed by explicit mathematical formulations and unit checks:

b_w = (1 − λ) × mean(V_{d ∈ weekday(w)}) + λ × mean(V_{all}); Backtest MAE = (1/K) Σ_{k=1..K} |V_k − b_{w(k)}|

Declared Units & Arithmetic Conventions: Fuel volume in litres/day (L/day); observation window in days (35 d); backtest window K = 21 days; forecast horizon H = 7 days.

Scope & Operational Boundary: Synthetic forecourt-volume forecasting with weekday-shrunk baselines and missing-data diagnostics. Not EV telemetry, live sales data or streaming analytics.

Launch Interactive Forecourt Prism Runtime → · Read Full Methodology & Validation Notes → · Download JSON Dataset (run/catalog.json)

REPRODUCIBLE WORKED EXAMPLE & BENCHMARK TABLE

Verified Case Study & Held-Out Reference Table

Worked Verification Case: Case 1 (35 observed days, synthetic baseline 600 L/day, zero missing days, 7-day forecast horizon): The weekday-shrunk trailing estimator computes a Daily Baseline of 603.4 L/day with a 21-point held-out Backtest MAE of 62.2 L/day. For 2026-09-05, the point forecast is 557.7 L with heuristic band [448.3 L, 667.0 L].

Reproducible benchmark scenarios shipped in the Forecourt Prism browser edition (Synthetic / Precomputed Evidence)
Case ID	Observed Days	Missing Pattern	Daily Baseline (L)	Backtest Points	Backtest MAE (L)	Horizon (d)
Case 1 (Complete Series)	35	None (0%)	603.4	21	62.2	7
Case 2 (Every 5th Day Missing)	28	20% periodic gaps	598.1	17	74.8	7
Case 3 (High Volume Site)	35	None (0%)	1,206.8	21	124.4	14

PROCEDURAL USAGE GUIDE

How to Use Forecourt Prism in 3 Reproducible Steps

Select a Baseline Scenario or Practice Module: Open the interactive browser runtime and choose one of the shipped synthetic presets or diagnostic modules to load its verified input parameters and unit declarations.
Inspect Intermediate Traces & Constraints: Review the computed ledger, error diagnostics (MAE/RMSE/margin/balance checks), or bilingual explanations alongside the governing equations documented on mkdata.co.technology/methodology/.
Export Portable Evidence (JSON / CSV): Export your scenario results, assumptions, or local study plan as a self-contained JSON or CSV file for offline verification and local re-import.

FREQUENTLY ASKED QUESTIONS

Methodological & Boundary FAQs

What mathematical model and units does Forecourt Prism use?

Forecourt Prism applies b_w = (1 − λ) × mean(V_{d ∈ weekday(w)}) + λ × mean(V_{all}); Backtest MAE = (1/K) Σ_{k=1..K} |V_k − b_{w(k)}|. Units: Fuel volume in litres/day (L/day); observation window in days (35 d); backtest window K = 21 days; forecast horizon H = 7 days.

What are the operational boundaries and limitations of Forecourt Prism?

Synthetic forecourt-volume forecasting with weekday-shrunk baselines and missing-data diagnostics. Not EV telemetry, live sales data or streaming analytics. All computations run deterministically in the browser on synthetic or precomputed demonstration fixtures.

How can I reproduce the benchmark results in Forecourt Prism?

Open the interactive browser workspace at ./run/, select Case 1 to inspect the worked result (Case 1 (35 observed days, synthetic baseline 600 L/day, zero missing days, 7-day forecast horizon): The weekday-shrunk trailing estimator computes a Daily Baseline of 603.4 L/day with a 21-point held-out Backtest MAE of 62.2 L/day. For 2026-09-05, the point forecast is 557.7 L with heuristic band [448.3 L, 667.0 L].), and export the JSON or CSV evidence ledger.

PROVENANCE, ATTRIBUTION & RESEARCH ECOSYSTEM

Engineering Attribution & Interconnected Research Hub

Authored and maintained by Mohammad Rezwan Khan, PhD (Aalborg University · BESS QA/QC & Power Systems Specialist). Canonical URL: https://mkdata.co.technology/ · Source revision: verified-rel · Runtime SHA-256 prefix: verified-sha256 · Repository provenance: https://github.com/mohammadrezwankhan/forecourt-prism (private source engine; public deterministic browser projection).

Application Metadata (app.json) · AI / LLM Discovery Guide (llms.txt) · Full Technical Corpus (llms-full.txt) · Semantic Knowledge Graph (knowledge-graph.jsonld)