P&G Canada (Walmart Canada replenishment team)
How High is High: Breaking the Negative Feedback Loop in Automated Replenishment
Identified a critical flaw in Walmart’s automated replenishment — $3M incremental revenue in 4 months.
Founder’s track record · Replenishment Analyst on P&G’s Walmart Canada team. The in-house operator experience Clarivant is built on.
The starting point
Walmart’s RetailLink replenishment was quietly killing P&G’s best stores. Bulky Femme Care products sat in backrooms; the system read low shelf sales as low demand, ordered less, and starved the shelf further. Golden stores spiralled toward single-digit weekly forecasts on demand that was really there.
The method
Across hundreds of SKU-store combinations, I built a custom On-Shelf Availability algorithm in R and KNIME that separated availability-driven low sales from genuine low demand, flagging stores whose decline matched the feedback-loop signature. Then I proposed a counterintuitive pilot — strategic overstocking of 10–20 products in ~20 golden stores — and staked my own neck on it: if it failed within a month, my manager and I would rent a U-Haul and buy back the excess ourselves.
The result
Overstocked stores recovered on the shelf within two weeks; Walmart asked to expand before the month was out. Scaled to all of Canada and then to Shaving — P&G’s highest-margin line — it drove $3M incremental revenue in 4 months (+4% in each category) and cut stockouts 10%, entirely from fixing an existing automation flaw, with no new products or promo spend. It won a Pearl Award and became standard practice for bulky, high-velocity categories.
“Arturo quickly became the go-to data person — organized, diligent, and a strong partner. We co-created ecommerce replenishment processes; his out-of-the-box thinking consistently improved how the team worked.”