Urban Outfitters Drops Shipping Costs by 7% with Algorithm

The secret is in avoiding the "lost sales" that occur when store inventory is used to fulfill online orders resulting in a stockout at physical locations.

Need to Know

  • Urban Outfitters reduced lost sales opportunities by 37% and shipping costs by 7% with a new algorithm from Celect, a predictive analytics platform for retailers.
  • Urban Outfitters used data science to optimize shipping locations according to stock, shipping, an customer location.
  • Online orders have low margins and high fulfillment costs due to shipping requirements, so ideally, retailers will minimize shipping costs by stocking stores strategically.

Analysis

Thanks to a study published in the Informas Journal on Applied Analytics by data scientists from Celect, Urban Outfitters has been able to reduce lost sales by 37% and shipping cost by 7%.

Celect is a cloud-based predictive analytics platform that helps retailers optimize their inventory through data-driven decisions, and was acquired by NIKE, Inc. in August of 2019.

Since the early days of e-commerce, retailers have been struggling and strategizing to figure out the best fulfillment patterns that can satisfy customers while keeping costs low and margins high. With same-day fulfillment of online orders rising and becoming the standard from a consumer standpoint, the algorithms needed to track staffing, warehousing, shipping cost and distance, margins, and stock needed to advance as well.

Celect found an answer in a robust algorithm that doesn’t require explicit demand forecasts, which retailers use to order stock and “safety stock”. This algorithm seeks to avoid lost sales, which is the result of using store inventory to fulfill an online order that then results in a stockout in the actual store, by using a rolling average of demand at every location when making a decision.

In both online and in-store scenarios, the more a retailer can use its current inventory to its’ full capacity, without marking it down, the better. The problem then becomes the location of the store inventory and how to use it most efficiently for online orders and ship it in the cheapest manner. 

“On the one hand, the goal of minimizing shipping cost may lead the retailer to consider shipping from the store nearest to the customer,” the researchers explain in their paper. “On the other hand, imagine that this nearest store is seeing high in-store sales of the same product, so that assignment to that store risks cannibalizing a future in-store sale. In the event that there exists an alternative location where inventory is plentiful relative to demand, an assignment to that alternate location might be preferred.”

Target is also a huge supporter of this store-centric fulfillment model and credits it with a 40% reduction in cost. Target CEO, John Mulligan, says that the retailer is planning to fulfill more than two-thirds of its e-commerce orders from stores, and are renovating 300 stores per year for this purpose. 

The paper concludes: “The fulfillment-optimization problem is not unique to Urban Outfitters: it is a practical consideration for any retailer with a nontrivial e-commerce business and a store network.” The quicker that retailers can see their digital and store stock, with predictions and estimates for delivery, whether the overstock is online or in-store, the less money will be lost all around.

With Urban Outfitters fulfilling an average of 18,000 orders a day and pulling in close to $4 billion in revenue for 2018, every margin matters.