15% assortment reduction while maximizing profit consistently.
Reliance on historical data created inefficiencies.
A major retailer with thousands of SKUs faced growing inefficiencies in assortment management. Their current pricing and inventory strategies relied on historical sales data but lacked insights into product substitutability, demand shifts, and overall performance. As a result, they struggled with poor inventory allocation, suboptimal pricing strategies, and declining profit margins.
Traditional methods failed to optimize assortment effectively.
Despite having vast amounts of sales and inventory data, the retailer struggled to make informed decisions about which products to promote, retain, or remove. Their static approach led to revenue loss and operational inefficiencies.Key challenges included:
- High fragmentation of SKUs: too many similar products cannibalized sales instead of completing the assortment.
- Overstock and stockouts: poor demand forecasting led to costly overstocking of low-value products and frequent shortage of high-demand items.
- Lack of visibility into SKU performance: decisions were based on basic sales figures rather than deeper insights into uniqueness, cross-product impact and demand balance.
- Unoptimzed pricing and promotions: lack of data-driven approach to adjusting prices and promotions for maximum margin and demand balance.
- Inconsistent decision-making: without AI-powered scenario analysis, adjustments to the assortment were based on intuition rather than predictive analytics.
This inefficiency led to inflated costs, reduced profit margins, and missed opportunities to optimize product offerings dynamically.
From data complexity to AI-driven precision.
To address the retailer’s inefficiencies, we developed an AI-powered SKU optimization model that analyzes multiple dimensions of product performance. Our approach focused on enhancing inventory, pricing strategies, and product assortment planning to maximize profitability and reduce waste.
Our approach included:
- Data-drive SKU analysis: aggregated historical sales, stock levels, and customer demand data to assess performance across all SKUs.
- AI-based substitutability insights: identified product relationships and cross-elasticity to determine which SKUs should be prioritized, adjusted or removed.
- Dynamic pricing optimization: leveraged predictive analytics to set optimal pricing strategies based on real-time demand and market conditions.
- Scenario planning & automation: simulated different listing and delisting scenarios to forecast impact on sales, margins, and inventory costs.
By combining AI-driven insights with strategic scenaroi planning, we empowered the retailer to make smarter, data-backed deicisons —enhancing profitability, reducing costs, and ensuring the right products are always on the shelves.
+1% increase in profit margins p.a.
The AI-powered SKU optimization solution transformed the retailer’s inventory strategy, delivering higher profitability, better stock management, and more efficient decision-making. By leveraging real-time insights, predictive modeling, and dynamic scenario planning, the company gained a clear, data-driven approach to assortment planning—reducing inefficiencies while maximizing revenue opportunities.
