Trusted by scaling brands
Everything you need for reliable demand planning
From data integration to forecasting, the complete demand planning solution.
The right forecast for every product
Lumina builds a bottom-up forecast from your sales history, configured to how your range is split and profiled and how your products behave: growth-adjusted seasonality for seasonal lines, rolling averages for stable ones, similar-product forecasting for new lines with no history yet. It tracks how each approach performs and switches to whichever is forecasting best, so the forecast matches your intuition about the range.
Plan at the level your decisions need
By week or by month, by product or by store, by channel or by retailer: forecast and plan at whatever granularity you need.
Forecasts aligned with your growth plans
Layer in your promotions, launches, and growth assumptions, and scale the forecast to your top-line plan. Compare actuals against plan against forecast, and override anything. It's transparent enough that you always know why the number is what it is.
I'd estimate Lumina saves 4-5 hours per week vs our old system.
Go deeper on demand planning
Guides, calculators, and definitions from the Lumina library.
Safety stock calculator
Compute safety stock and reorder point with the standard Z × σ × √LT formula. Optional lead-time variability for the full version.
ExploreGlossaryForecast accuracy
How close your forecasts come to actual demand, why the headline number is the wrong focus, and what to track instead.
ExploreSolutionInventory management for ecommerce
Multi-channel inventory planning for scaling brands selling across Shopify, Amazon, and wholesale.
ExploreGlossaryDemand variability
How much demand bounces around its average: the input that decides how much safety stock you need.
ExploreGlossaryForecast bias
The systematic over- or under-shoot in your forecast. Worse than noise, and the cause is usually organisational.
ExploreCompareLumina vs NetStock
Lumina and NetStock side by side: features, pricing, onboarding, and fit for scaling brands.
Explore