Retail AI & Shelf Intelligence

AI-powered shelf monitoring produced a flood of scan data but not decisions. Store and category leaders couldn't tell what to fix first or how large the addressable opportunity was, and brand-side sponsors funding the programs couldn't see their attributable ROI separately from losses they couldn't influence.

I came at it from the operator seat — time-and-motion observation in pilot stores, and separate conversations with store operators, category leads, and brand-side stakeholders to map what each actually needed from the data. I deliberately grounded the analytics in published academic out-of-stock research rather than vendor benchmarks, so the numbers would hold up under executive scrutiny.

Led the out-of-stock / lost-sales analytics methodology that turned raw CV scans into prioritized, dollar-quantified actions, and separated the losses store execution can recover from the ones it can't. Brought operator judgment to the product itself: when an AI-reset workflow's labor-savings case didn't account for how resets actually get done on the floor, I used field evidence to redirect the bet before it went to market. Earlier, from the customer-success seat at a computer-vision retail company, I introduced a self-serve onboarding feature, Planogram Scan-in, that let retailers build their store planograms by scanning shelf UPCs — giving the models the canonical item-location data they lacked.

• Built an out-of-stock / lost-sales analytics approach that became a reusable internal standard across enterprise grocery pilots
• Made brand-side ROI legible by separating recoverable store-execution losses from non-recoverable supply-chain losses
• Redirected an AI-reset product bet on field evidence — caught an overstated labor-savings case before it reached the market
• Shipped Planogram Scan-in, the onboarding feature that unblocked CV deployments missing canonical planogram data