A large, multi-brand enterprise apparel and accessories retailer had come to the realization that it needed to leverage product attribute data in order to improve its demand forecasting. The retailer’s forecast accuracy for new products had been approximately 30%, due to relying on manual processes and minimal data. When generating a new product forecast, the retailer would start by manually finding a “look-alike” product or proxy product – a tedious, time-consuming and subjective process that they knew needed to be addressed. The company had been building their own internal algorithm for demand forecasting, yet couldn’t proceed effectively without enriched product data to help better predict and forecast sales.
The company turned to Lily AI and its Demand Forecasting capabilities to ensure that its forecasting model would be accurate and could scale to support the 34,000+ product catalog each year.