The multichannel retailer, OTTO, offers its customers more than 2.2 million items from 6,000 brands in its online shop, otto.de. This includes items from its select partner retailers. OTTO uses Blue Yonder’s machine-learning solutions for accurate demand forecasts of its own products and has been doing so for several years. It has now expanded its use of Blue Yonder’s machine learning solution to goods from its partner retailers, providing automated replenishment across all products.
Items purchased through its partner retailers once took five to seven days to reach the customer. Since automating the process with Blue Yonder, OTTO has been able to deliver third-party items in one to two days, without risking overstocking at the warehouse. The result is a better customer experience and increased demand for the diverse products of its own, and partner, brands.
Which articles will be sold in the coming days, how often, in what size, colour and quantity? Accurate demand predictions based on a multitude of factors is key to OTTO’s success, especially in fashion and electronics retail sales. At OTTO, around 200 factors are considered to create accurate demand forecasts for goods. Blue Yonder Replenishment Optimization then uses those forecasts to deliver automated decisions – “and with an extremely high rate of accuracy” said Michael Sinn, director of category support at OTTO.
Historical data just scratches the surface when it comes to producing precise decisions.
For its predictions, Blue Yonder analyses around three billion transactions from past sales, prices and stock levels.
“The benefits of automated decisions becomes evident when you put it into practice,” said Mr Sinn. “We consider it accurate when we sell out of items ordered from our retail partners within 30 days. With automated replenishment decisions from Blue Yonder, we achieve this 90 percent of the time. This is extremely valuable for us.”
Increasingly, the goods bought based on Blue Yonder’s automated decisions are not even put into storage. Instead, they are sent directly to the customer.
AI ensures faster delivery times, fewer returns and a reduced carbon footprint in the delivery chain
Delivery times are now drastically shorter: From as many as seven days down to one to two days. With quicker delivery, OTTO has also seen its customer satisfaction improve, along with increased demand for its products.
Blue Yonder’s Replenishment Optimization impacts other areas as well. With automated replenishment decisions, OTTO has seen a decreased number of returns because their customers are receiving goods that are the right size, the right color and fit their expectations. Suppliers, retailers and customers all benefit from an improved delivery process by optimizing the number of items sent to the customer. It reduces shipping costs and the carbon footprint of transporting the items.
“OTTO’s strategy shows how imperative machine learning is to improving customer satisfaction,” said Prof. Dr. Michael Feindt, Chief Scientist and Founder of Blue Yonder. “Everyone profits from automated replenishment processes: The customers through shorter delivery times, the suppliers through improved planning oversight, as well as higher demand. OTTO gains through lower warehouse and shipping costs.”
Blue Yonder ensures a high degree of automation
OTTO also benefits from a low-maintenance system. Blue Yonder’s algorithms learn from historical sales data and stock levels to constantly improve its sales forecasts. “Even special sales promotions like the increasingly popular ‘Black Friday’ can be factored in,” says Sinn. “We’re very happy with this system as we’ve been able to use it to automate replenishment processes, a critical element for any online retailer.”
So far, OTTO has used the solution in the distribution centers for ordering fashion and multimedia items from third-party sellers. It is looking to expand its application to its own offerings. OTTO has also been able to continuously increase the number of suppliers using the reliable system.