AI in FMCG: Demand, Merchandising & Marketing |…

AI in FMCG: Demand, Merchandising & Marketing

Latest update: November 2025

AI is helping FMCG companies more accurately forecast demand, plan production, optimize merchandising and improve promotional effectiveness.

Promo Mix & Personalization for Categories/Channels.

Data? Sales by SKU channel, promotions, stock levels, distribution.

Metrics? MAPE, OSA/OSA-loss, uplift, promo ROI.

live demo · related simulation● LIVE

Risks? Data Noise, Out-of-Stock, Promo Cannibalization.

Pilot time? 6–12 weeks.

Scaling? MLOps, feature stores, scenario simulations.

Frequently asked questions

What is OSA control in FMCG?

OSA control involves monitoring and mitigating promotional skewness to optimize sales performance.

How can computer vision be used in retail to detect out-of-stocks, and for replenishment planning?

Computer vision systems can automatically identify out-of-stock situations on shelves and provide real-time data for optimizing inventory levels and replenishment schedules.

How can promo effectiveness be measured and optimized using AI models?

Promo effectiveness is assessed by analyzing the incremental sales lift generated by promotions, allowing companies to identify the most impactful campaigns and adjust strategies accordingly.

What are uplift models and how can they be used to determine the optimal promo mix considering price elasticity?

Uplift models predict the incremental sales impact of a promotion, taking into account each customer’s individual response – or ‘elasticity’ – to pricing changes. This allows for highly targeted promotional offers.

▶ Try it live

Everything above runs in your browser — open Hash Function Avalanche Visualizer and change the parameters while it is running. Nothing is installed, nothing is uploaded, the whole model lives in one tab.

▶ Open Hash Function Avalanche Visualizer simulation