What Solutions a Subsidiary of Walmart, ASDA Leverage to Address Picking Optimization Issues 

ASDA, a British supermarket retailer, operates online grocery delivery and pick up services at over 300+ stores delivering more than a billion items across thousands of trucks trips each year. ASDA became a subsidiary of Walmart after a takeover in July 1999 and currently positions at 3rd rank by market share in the UK. 

Customers can order grocery through ASDA grocery website. And for that, they have to first create their cart and book an appointment to receive their order at home. A location routing engine would generate optimized routes based on the incoming orders with fulfilment processes working towards ensuring that these trucks are loaded and sent on their way, on-time. The picking optimization engine specifically deals with optimizing how these grocery orders are picked by store links minimizing the time required to pick them. 

However, picking grocery efficiently poses several challenges and some of the main challenges with the picking optimization problem arises due to the fact that picking was executed in retail-stores and may of the design decisions couldn’t be impressed upon. The same issue befell with ASDA. 

The Business Challenge

The picking process tends to be manual not only augmenting fulfilment costs but also restraining revenue opportunities creating bottleneck around the picking process to the number of orders that could be promised to customers on the website.

The ASDA challenges also include: large order sizes, cold chain compliance, complexity of batching orders, locating items on the shop floor, store environment, limitations of the picking process, complex cost function and low tote fills and low pick rates. 

The Solutions

Mitigating the challenges, ASDA decided to leverage a complex yet practical suite of machine learning, genetics and metaheuristic optimizations. By utilizing the solution, the picking optimization has been successfully running for the last few months in ASDA stores.

Technology – The technology framework that supports the picking optimization landscape is built with multiple failover mechanisms that runs on various clusters of servers ensuring that intricate computations are implemented fast and service level agreements are met. A series of alerting and monitoring systems support the technology framework at crucial junctions. Several micro services supporting complex store layouts, route visualizations, store profiler, volumetric, shortest-paths, among others are tightly coupled with the optimization engine to provide essential data for the optimization function.

The Outcomes

After leveraging suite of machine learning, genetics and metaheuristic optimizations, ASDA sees benefits of Increased pick speed; Reduced walk time; Higher utilization of trolleys and totes; and Better utilization of trolleys.