AI Case Study
Otto predicts with 90% accuracy what products will be sold within 30 days driving automated purchasing and reduction of annual returns by 2M
Otto, a German ecommerce retailer, was struggling to lower the millions in annual costs of product returns. Consumers would often return shipments if they took more than a few days or they they received multiple shipments. This was especially true of third party products where Otto had less control over inventory availability. Using a deep learning algorithm based on CERN particle physics experiments their models could predict with 90% accuracy what would be sold within 30 days. This allowed them to automatically purchase 200,000 items a month from third party retailers.
Consumer Goods And Services
"Its conventional data analysis showed that customers were less likely to return merchandise if it arrived within two days. Anything longer spelled trouble: a customer might spot the product in a shop for one euro less and buy it, forcing Otto to forgo the sale and eat the shipping costs.
But customers also dislike multiple shipments; they prefer to receive everything at once. Since Otto sells merchandise from other brands, and does not stock those goods itself, it is hard to avoid one of the two evils: shipping delays until all the orders are ready for fulfilment, or lots of boxes arriving at different times.
The typical solution would be slightly better forecasting by humans of what customers are going to buy so that a few goods could be ordered ahead of time. Otto went further and created a system using the technology of Blue Yonder, a startup in which it holds a stake. A deep-learning algorithm, which was originally designed for particle-physics experiments at the CERN laboratory in Geneva, does the heavy lifting. It analyses around 3bn past transactions and 200 variables (such as past sales, searches on Otto’s site and weather information) to predict what customers will buy a week before they order."
Budgeting And Forecasting
"Big data and machine learning have been used in retailing for years, notably by Amazon, an e-commerce giant. The idea is to collect and analyse quantities of information to understand consumer tastes, recommend products to people and personalise websites for customers. Otto’s work stands out because it is already automating business decisions that go beyond customer management. The most important is trying to lower returns of products, which cost the firm millions of euros a year."
"The AI system has proved so reliable—it predicts with 90% accuracy what will be sold within 30 days—that Otto allows it automatically to purchase around 200,000 items a month from third-party brands with no human intervention. It would be impossible for a person to scrutinise the variety of products, colours and sizes that the machine orders."
"The new AI system has reduced product returns by more than 2m items a year. Customers get their items sooner, which improves retention over time, and the technology also benefits the environment, because fewer packages get dispatched to begin with, or sent back."
"A deep-learning algorithm, which was originally designed for particle-physics experiments at the CERN laboratory in Geneva, does the heavy lifting to predict what customers will buy a week before they order."
Otto "analyses around 3bn past transactions and 200 variables (such as past sales, searches on Otto’s site and weather information)."