Lily AI Demand Forecasting Provides Accuracy at Scale, Driving 7-8 Digit Revenue Lift for Multi-Brand Apparel and Accessories Retailer


3 to 1 month

reduction in forecasting timelines

Up to $48M

in projected topline revenue

The Problem

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 integral 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.

The Solution

Lily AI began by ingesting and processing the retailer’s previous season’s products in order to establish a historical data set. The retailer then sent Lily AI product renderings or images for their new products, then ran this set of product data through Lily AI’s proprietary product similarity and tagging pipelines that compared the new products against the historical data set.

Lily AI used this data set to identify the most similar products—or proxy products—which were then assigned a “similarity score.” The retailer then used this similarity score and similar products that Lily AI provided as an input for demand forecasting for upcoming seasons, with a goal of accurately determining proper quantities to procure and then allocate effectively.

The Results

With Lily AI’s demand forecasting and associated proxy products, this retailer was able to reduce its forecasting timelines from 3 months to 1 month with automation at scale. Lily AI was able to replicate the proxy product predictions of their best merchants, now relying on data that drove even higher accuracy levels. This increase in accuracy and time savings in the forecasting pipeline resulted in the right products being ordered at the right time, as well as the ability to get ahead of supply chain orders and sell more products at full margin.

By utilizing Lily AI product data for demand prediction and forecasting, this is projected to positively impact this retailer’s topline revenue by $7-$48 million. 

We hired Lily AI to feed its extensive product attribution data into our demand forecasting algorithms to truly ensure that we’re ordering the right products at the right times. They’re helping us move away from manual demand planning, and their extensive visual similarity models to identify proxy products dramatically reduces our planning cycles and manual product identification.”

Learn more about accurately connecting your shoppers with the products they’re looking to buy.

Request A Demo