AI for retail that moves the forecast, not the slide deck.

The honest answer is narrower than the market claims and more durable than the sceptics allow. In retail and FMCG, AI moves the needle where a decision is repeated thousands of times a week, where the input is already digital, and where a small, consistent improvement compounds. Hierarchical demand forecasting is the clearest example: individually each judgement is unremarkable, but at volume the difference between a good model and a mediocre one shows up directly in forecast accuracy (WAPE) and on-shelf availability.

What AI does not change is accountability. A model can rank, score, flag and draft; a person still owns the outcome. The engagements that survive are the ones that design the human-in-the-loop contract first — who reviews what, at what threshold, with what escalation — and then fit the model to that contract. Doing it the other way round produces an impressive pilot and an abandoned system.

Almost every stalled AI programme in retail and FMCG stalled on data, not on modelling. SKU × store × week sales panels, promo calendars and weather feeds arrive with gaps, duplicated identifiers, schema drift and undocumented business rules embedded in decade-old integrations. Our first phase is always a data readiness assessment: what exists, what is trustworthy, what has to be instrumented, and what the model will simply never see.

That assessment is deliberately unglamorous and it is where the risk is removed. It tells you whether the problem is tractable at all, what the realistic ceiling on forecast accuracy (WAPE) and on-shelf availability is, and what it would cost to lift that ceiling. Clients regularly change scope after it — which is exactly the point of doing it before, rather than after, six months of model development.

Systems in retail and FMCG are inspected. GDPR and consumer-data transparency rules set the bar for what has to be shown: how the model was trained, on what population, with what known failure modes, monitored how, and rolled back by whom. We produce that evidence as a deliverable alongside the model, not as a retrospective scramble.

The final phase is handover. Your team receives the training pipelines, the evaluation harness, the monitoring dashboards and a runbook written for an on-call engineer at three in the morning. A system your own people cannot operate is not a delivered system, whatever the acceptance certificate says.