I deployed a forecasting pipeline at The Feed that predicts stock and demand across every SKU. It reads historical orders, current on-hand inventory, and regional demand, and hands the operations and purchasing teams a forecast they can actually order against, so reorders reflect where demand is heading instead of a trailing average. Surfacing forecast-vs-actual right inside the reporting layer is what pulled the inventory discrepancies down.
The Feed builds, warehouses, and ships fuel for endurance athletes, and it's growing fast. I work on the operations software that lets it scale, the reporting leadership trusts, the forecasts purchasing orders against, and the fulfillment logic that keeps orders on time. I like this kind of software because the result is physical: boxes out the door, hours saved, a shelf that doesn't run empty.
Browse the full collection →