Shipping costs are a significant factor in impacting profit margins of e-tailers. Retailers who have a physical presence as well as an online presence, have the option of shipping items from a store in addition to shipping from one of the central warehouses. The ship-from-store model is the strategy which brick and mortar retailers, both big and small, can employ to remain competitive in the digital age.
About the Client
A prominent North-American clothing retailer. The retailer has brick and mortar stores across the country in addition to an online store.
In clothing, it is common for nearly half of the orders to have more than one item. Also given the variety of items available online, it is often the case that there may not be any store which has all the items in an order or may not be in stock. In such a case, the order needs to be split across multiple stores.
The decision of how to best fulfill an order is complex due to the number of considerations involved, like:
Reduction of time for goods to reach the customer.
Shipping costs, which is dependent on distance and package size for each shipment.
Minimizing the number of separate shipments – receiving multiple packages at different times for the same order tends to annoy customers.
Inventory optimization – Shipping items from stores that have excess inventory, reduces both inventory costs and chances of out-of-stock situations in stores.
There are naturally trade-offs as reducing transit time might imply shipping the order in 3 shipments from 3 nearby stores, but the shipping cost will be high and the customer may get annoyed by 3 separate deliveries for one single order.
On the other extreme, shipping the entire set of goods in one shipment from a central warehouse may be ideal to reduce the number of shipments, but it does not allow for store inventory to be best utilized.
Arriving at a best solution requires allowing the business to decide the trade-offs by setting weights for different objectives.
Our approach involved the following steps:
Developing a suitable objective function via simulation where we developed a simulation framework that allowed the business to test-drive the optimization and experiment with different relative weights for the various objectives.
An interface to allow the user to tune the weights of different components of the objective function.
Application of business constraints and search for feasible solutions.
The business objective was a combination of the number of separate shipments, shipping time, shipping cost, order margins and store inventory levels.
The algorithm would process a batch of new orders every 30 mins to an hour.
No human decision making was involved.
About US$1M in savings per year through a combination of improved order margin and shipping costs while minimizing the number of split orders (separate shipments to a customer).
Dr. Rohit Lotlikar is a highly experienced machine learning scientist and brings nearly two decades years of varied experience in building data driven intelligent business solutions.
Dr. Lotlikar has B.Tech. and M.Tech degrees in Electrical Engineering from IIT-Bombay and a PhD in Machine Learning from the University of Cincinnati.
His professional interests and expertise includes investigating and exploiting patterns in data and human behaviour to build data driven decision making/support systems, particularly as applied to understanding customer behaviour, digital marketing and workforce optimization. His experience spans working at startups developing machine-intelligence based products, developing innovative technologies at IBM Research and most recently in management consulting as a director in the analytics practice at Ernst & Young.