Demand-to-Shelf.

Never out of stock at peak.

The right product, to the right distributor, at the right time.

Forecasting and stock allocation for Kokuyo Camlin, redesigned around real demand instead of a flat budget. Built by dataeze, the team already running your Camlin BI.

Today, the budget-gap model fills barely half of demand lines.

On a live shadow run on your Camlin server (23 Jun 2026, 11,692 distributor-SKU lines), the current budget-gap allocation reaches a fill rate of just 52.6%, the share of demand lines the depots actually serve. It is mis-targeted, not just under-supplied.

Lines are auto-zeroed once billing crosses the monthly budget which, in a back-to-school ramp, usually means the budget was set too low, not that the distributor is stocked. Across this run distributors were collectively at ~95% of plan (15,61,420 sold vs 16,40,044 planned units) but very unevenly, so the same logic over-orders the overstocked and starves the ones about to run dry. It is a decision-logic problem, not a warehouse problem.

One blunt rule decides every depot's split.

Monthly budget − billed so far = gap to budget. That single signal splits depot stock pro-rata to the gap. Transparent and cheap, but blind to the four things that actually cause stock-outs:

requirement = max(month_budget − billed_so_far, 0); each depot's stock for a SKU is split across active distributors in proportion to that requirement, capped at it, zeroed if the depot is empty. It is a fair-share rationer, not a stock-out-prevention system.

From Budget-to-Depot, to Demand-to-Shelf.

Same data to start. Different question. Today the system answers "who is behind budget?" Tomorrow it answers "who is about to stock out at peak, and which truck stops it."

A forecasting brain turns history, seasonality and the school calendar into a demand signal with an explicit confidence band. That feeds an allocation engine that sizes a target (cycle + safety stock, capped at 45 days of cover), nets off what is already on the way (open orders), blends the 90-day off-take 70/30 with the budget signal, and under scarcity protects the distributors most likely to stock out before chasing budget attainment. The output is cartons to ship, not a chart of the old plan.

We don't drop a model on messy data.
We earn the accuracy first.

A forecast is only as trustworthy as the data and definitions beneath it. This is the pipeline we run before a single carton is ever recommended, on the very same SQL you already have.

The semantic layer is why the forecast answers like your best planner, not a black box.

A forecast that earns its place, every month.

Runs on SQL plus Python, no server change needed to produce and validate it. Every cell is probabilistic, so the safety buffer is derived, not guessed.

The budget is flat. Demand is not.

A 1/12 flat budget structurally under-feeds the Mar to Jul back-to-school peak, where the money is, and over-feeds the trough. Our engine rides the curve.

The engine de-seasonalises history to a clean base rate, then re-applies a seasonality index at ruling level for the planning month, so the signal rises and falls with real demand instead of a calendar-blind twelfth.

We know when the school bell rings.

A single national budget smears the country's reopening regimes together. A region-keyed reopening signal sharpens each depot's curve to its own calendar.

School-reopening windows, board/exam schedules, festivals and monsoon onset are encoded as learnable regressors at region-by-ruling level, refreshed annually from public board, IMD and tender sources in a short calendar-update ritual. This is the moat a generic time-series vendor will not build.

Scarce stock goes where it prevents the most stock-outs.

Under scarcity, the norm at ~53% fill, pure pro-rata spreads the shortage evenly and silently manufactures stock-outs. The waterfall changes the objective:

Plus executable guard-rails: case-lot rounding, an over-stock cap (no channel-loading), inter-depot balancing and same-family substitution.

Same depot stock. 20 points more fill.

Live shadow run on your Camlin server, 23 Jun 2026: 11,692 distributor-SKU lines, the identical set under both models. Every allocation respects depot stock, zero supply-safety breaches, independently re-checked. Planning and recommendation only; execution stays with your team.

The decision, made visible per distributor.

Real lines from the 23 Jun 2026 shadow run (distributor names masked). The budget-gap model ships zero to fast sellers who passed plan; Demand-to-Shelf recovers them and protects dry distributors to a minimum cover. Full per-line view in the companion Excel. Recommendations only; execution stays with your team.

We use primary data today. Secondary is the accelerant.

Where we say days-of-cover or run-rate today, it is an estimate inferred from primary, made precise once secondary is captured. Missing ground data is a roadmap, not a blocker.

A roadmap that proves value before it touches your server.

Each step adds measurable rupee impact. The first two run now, on data you already share; the rest unlock as we capture ground data through a live, mobile-optimised template.

Phases 0–1 run now on the base data you already share (the ₹4.37 Cr is simulated on your live primary billing at ₹26/unit). For Phases 2 and 4 we provide a live, mobile-optimised capture template (distributor closing stock, raw-material) so ground data flows in without disrupting your team. Today's pro-rata logic stays as the cold-start fallback throughout: capability is layered on, nothing is ripped out.