Forecasting app
Interactive data demo
Univariate demand curves with honest baselines—not neural nets: resampled Holt-Winters by day/week/month only when seasonality is supportable; Plotly band with MAPE/MAE against naive; warnings and fallback reasons stay visible for operators validating the forecast.
Commercial fit
Shows the same transparency rules as storefront forecasting work—honest baselines when seasonality breaks, artefacts (CSV + JSON summaries) reviewers can replay, escalation to stronger ML milestones only via a new written scope—not silent model creep.
Reference overview
Univariate demand curves with honest baselines—not neural nets: resampled Holt-Winters by day/week/month only when seasonality is supportable; Plotly band with MAPE/MAE against naive; warnings and fallback reasons stay visible for operators validating the forecast.
Handoff notes
Sidebar-triggered run exports forecast CSV plus summary JSON. Bundled sample series and CLI smoke live in-repo; promo or holiday regressors stay out of scope with explicit naive fallback when fit is weak.