Profit per SKU across three marketplaces, checked against manual figures

The task

A home-goods manufacturer sells through five seller accounts on three marketplaces and had no reliable profit per SKU. Statements differ by platform, some operations settle in another month, and ad spend and account fees never reached products. Excel reconciliation took days and still drifted. They needed one source of truth for profit, a demand forecast for purchasing, and a check on marketplace overcharges.

What we built

• One pipeline for all five accounts: 12 months of history, daily refresh, restart-safe jobs. Marketplace access is read-only, and nothing in the seller accounts is ever changed.
• We rebuilt the platform’s monthly statement logic and checked it against the client’s own numbers, day by day and SKU by SKU. COGS comes in as a file from the client’s ERP, as agreed.
• A 7–30 day demand forecast: models are compared with a naive forecast on a held-out period and the acceptance metric is computed automatically. The model has not yet reached its accuracy target, so the seller dashboard signals come from a deterministic heuristic.
• Stock-out signals and a trend detector, both backtested on history. Commission, logistics and storage are checked against the platform’s tariff, which gives a ready basis for claims.
• A role-based dashboard, an AI assistant over account data, alerts to Telegram and email, a weekly P&L. Acceptance ran on measurable KPIs, with weekly demos and automated tests in CI.

Outcome

0.00%

variance vs the client’s manual benchmark across units, revenue, COGS, profit and margin for a control SKU over a month; the threshold was 1%

1.18M rows

of sales across 5 accounts and 12 months processed; 10.7% were ordered and settled in different months

~7.5% of spend

in one account’s monthly statement never reached the SKU report (no SKU attached). We found it and included it in total spend; reconciled down to one control line

Services

More cases