Walmart
Canvas Category OEM : Retail
What started small, with a single discount store and the simple idea of selling more for less, has grown over the last 50 years into the largest retailer in the world. Each week, approximately 220 million customers and members visit approximately 10,500 stores and clubs under 48 banners in 24 countries and eCommerce websites. With fiscal year 2021 revenue of $559 billion, Walmart employs over 2.3 million associates worldwide. Walmart continues to be a leader in sustainability, corporate philanthropy and employment opportunity. It’s all part of our unwavering commitment to creating opportunities and bringing value to customers and communities around the world.
Assembly Line
Using Predictive and Gen AI to Improve Product Categorization at Walmart
To optimally use the limited display space and enable customers to discover the most pertinent and appealing products within each department, we developed Ghotok, a cutting-edge AI technique which can effectively analyze and understand the relationships between different products and categories. The ultimate goal of this project is to save customers’ time by making their online shopping experience more efficient and fun.
Ghotok’s objective is to consider domain-specific contextual information to understand the many-to-many relationships between two different types of product hierarchies (that is, Category and Product Type) pairs. To achieve this, Ghotok incorporates advances in both Predictive and Generative AI techniques to find the most relevant product types for each category. Instead of choosing one single model for both Predictive and Generative AI, we use an ensemble of models. Ensemble models are a machine learning approach that combines multiple ML models to make predictions. The goal of ensemble learning is to combine the outputs of diverse ML models to create a more precise prediction. One benefit of this approach is that it dispenses with the requirement for customer engagement data (which is noisy as sometimes customers might click on items by mistake or out of curiosity) by leveraging a limited amount of human-labeled data. This makes the model effective for both frequently and rarely visited parts of our product hierarchies.
A Fork in the Road: Walmart Bets on Associates, Automation
After a 16-month proof of concept, I’m proud to announce Walmart is taking another step into the future, rolling 19 autonomous forklifts across four high-tech DCs, with the potential for more as we evaluate the benefits to our associates and operations. As our facility has worked with Fox Robotics, the developer of the autonomous forklifts, we’ve learned a lot. But I can sum it up easily: Automation isn’t just good for business – it’s good for our associates too.
Here’s how they work together: Trucks arrive at our DC, and they need to be unloaded. Queue the forklifts. Using AI-powered machine vision and dynamic planning, the forklifts safely and accurately unload pallets and ferry them to be inducted into the automated storage and retrieval system, which catalogues and stores our goods. And the associate? They’re the most important part.
Associates are being trained to operate the FoxBot autonomous forklift, designed to fully automate the warehouse loading dock. And so far, it’s working. That’s why Walmart invested growth capital for a minority stake in Fox Robotics, demonstrating a multi-year commitment to the company and its technology.
Walmart and unspun Collaborate on 3D Fabric Weaving Technology
Walmart, the world’s leading omnichannel retailer, today announced a pilot project with unspun, a pioneering fashion tech company using the world’s first 3D weaving technology, a collaboration that, if successful, could help reduce the environmental impact of garment production, offer a more sustainable process for meeting apparel demand and support the companies’ shared commitment to shift more textile manufacturing back to the U.S. Out of its micro factory in Oakland, California, unspun’s first-of-its-kind technology promises to more quickly and efficiently transform yarn into garments.
In the pilot project, the two companies will explore how unspun’s 3D weaving machines can be used to make workwear style pants under a Walmart house brand. With 3D weaving, yarn is spun directly into completed garments. This is an innovative and new approach to garment manufacturing. Traditionally, yarn is woven into one-dimensional fabrics, which are then cut and assembled into garments – creating waste and taking significant time and multiple manufacturing steps. The 3D weaving process is different from commonly known 3D printing, which creates a physical object from a digital design by laying down thin layers of liquid or powdered plastic, metal or cement.
Walmart’s Earnings Call Is A Delight For Supply Chain Professionals
After having too much inventory for several quarters, driven by supply/demand mismatches caused by COVID, they returned to inventory efficiency. The world’s largest retailer had lower markdowns, improved in-stock service levels, and lower inventory. Walmart’s U.S. inventory was down 4.5%, Sam’s was down over 8%. In the US, the company is investing in automation that they predict will lead to a higher level of inventory accuracy over the next few years. Walmart reports that investments in artificial intelligence have also improved inventory management.
Sam’s Club performed 35 million fewer tasks in the store last year. A lot of that was artificial intelligence that helped associates manage inventory better. They also report using RFID and computer vision, as well as digital displays and labels, to improve operations. New digital tools that automate repetitive tasks or eliminate heavy lifting have increased associate productivity and customers are benefiting from improved in-stock rates and associate accessibility, leading to customer experience scores up over 140 basis points in fiscal year 2024.
On the logistics front, the retail behemoth reports that they have retrofitted 13 regional distribution centers with varying levels of automated storage and retrieval systems. They are implementing technology from Symbotic in a phased deployment. The level of automation in a Symbotic solution is hard to grasp; it really has to be seen to be believed.
Canoo takes it one vehicle at a time
The first vehicles assembled at Canoo’s manufacturing facility were on display Wednesday inside its 630,000-square-foot plant as part of a batch in an agreement for up to 1,000 vehicles with the state of Oklahoma. In August 2022, Canoo announced an agreement with Walmart for 4,500 vehicles. Also last year, the U.S. Army awarded Canoo a contract to test its pickup truck.
In August, the company announced it signed agreements on incentives with the state for its vehicle assembly facility in Oklahoma City and a battery module manufacturing plant in Pryor with a combined value of up to $113 million for 10 years. The agreement has multiple benchmarks Canoo must meet to receive the funds. The battery plant and the assembly facility will bring more 1,300 jobs, according to a release.
The Season of More: Unwrapping Our Plan for Speed, Accuracy and Availability
To start, we’ve invested in an AI-powered inventory management system that positions products according to customer demand. It’s patent-pending, so we’re confident it has set us up for success heading into the season and will continue to do so as holiday shopping kicks into high gear. For example, our AI can recognize a top-selling toy in a particular region, and automatically send more items to those stores. And if a toy is selling better in the Midwest compared to the East Coast, we can reposition inventory to that area of the country.
Additionally, we continue to rapidly expand the use of next-generation technology in our distribution centers. This year, over 15% of stores will receive merchandise from automated distribution centers, helping to get items off trucks and onto the sales floor faster and more efficiently. These centers play a pivotal role in stocking our stores while making it easier for associates to unload trucks and sorting products for hours. Instead, they can simply bring department-ready pallets directly to the sales floor, accelerating how quickly we can deliver products to stores and customers.
Machine Learning Platform at Walmart
Walmart is the world’s largest retailer, and it handles a huge volume of products, distribution, and transactions through its physical stores and online stores. Walmart has a highly optimized supply chain that runs at scale to offer its customers shopping at lowest price. In the process, Walmart accumulates a huge amount of valuable information from its everyday operations. This data is used to build Artificial Intelligence (AI) solutions to optimize and increase efficiencies of operations and customer experience atWalmart. In this paper, we provide an overview of the guiding principles, technology architecture, and integration of various tools within Walmart and from the open-source committee in building the Machine Learning (ML) Platform. We present multiple ML use cases at Walmart and show how their solutions leverage this ML Platform. We then discuss the business impact of having a scalable ML platform and infrastructure, reflect on lessons learnt building and operating an ML platform and future work for it at Walmart.
⛓️🧠 Multinationals turn to generative AI to manage supply chains
Navneet Kapoor, chief technology officer at Maersk, said “things have changed dramatically over the past year with the advent of generative AI”, which can be used to build chatbots and other software that generates responses to human prompts.
New supply chain laws in countries such as Germany, which require companies to monitor environmental and human rights issues in their supply chains, have driven interest and investment in the area.
📦 Inside Walmart’s Warehouse of the Future
“What this technology does for us is increases capacity, increases the accuracy of our loads, increases the speed of the supply chain and lowers cost,” said David Guggina, executive vice president of supply chain for Walmart. It is “also completely reshaping the way that our associates work within the distribution center.”
Kyle Silberger transferred from unloading trucks manually to what Walmart calls an “automated cell operator” about a year ago. “It’s easier physically and harder mentally,” said the 30-year-old who has worked at the warehouse for nine years. “It’s sort of autopilot on the loading dock,” he said, describing his former role.
Expanding Walmart’s Market Fulfillment Center Capabilities Through Automation
Today, we are announcing a step forward in the evolution of our supply chain and MFCs. I’m pleased to announce that Walmart has agreed to acquire Alert Innovation, a robotics automation company that develops material-handling technology for automating order fulfillment in retail supply chains. Walmart has been working with Alert to customize technology for our MFCs since 2016. Further investing in this technology will enable us to leverage our store footprint – 4,700 stores located within 10 miles of 90% of the U.S. population – for storage and fulfillment. For customers, this means orders can be fulfilled quickly and conveniently through pickup and delivery, giving them the items they want, when and where they want them. This system also enhances the experience for associates, who are integral to helping us perfect the system.
Walmart Amps Up Cloud Capabilities, Reducing Reliance on Tech Giants
Walmart Inc. says it has developed the capability to switch seamlessly between cloud providers and its own servers, saving millions of dollars and offering a road map to other organizations that want to reduce their dependence on giant technology companies.
Walmart and Symbotic Expand Partnership to Implement Industry-Leading Automation System
Symbotic LLC, a revolutionary A.I.-powered supply chain technology company, and Walmart Inc. announced an expanded commercial agreement to implement Symbotic’s robotics and software automation platform in all 42 of Walmart’s regional distribution centers over the coming years. This is an expansion of Walmart’s prior commitment to deploy Symbotic Systems in 25 regional distribution centers.
How Walmart Uses Apache Kafka for Real-Time Replenishment at Scale
Real-time inventory planning has become a must for Walmart in the face of rapidly changing buyer behaviors and expectations. But real-time inventory is only half of the equation. The other half is real-time replenishment, which at a high level, we define as the way we can fulfill the inventory demand at every physical node in the supply chain network. As soon as inventory gets below a certain threshold, and based on many other supply chain parameters like sales forecast, safety stock, current availability of the item at node and its parents, we need to automatically replenish that item in a way that optimizes resources and increases customer satisfaction.
On any given day, Walmart’s real-time replenishment system processes more than tens of billions of messages from close to 100 million SKUs in less than three hours. We leverage an array of processors to generate an order plan for the entire network of Walmart stores with great accuracy and at high throughputs of 85GB messages/min. While doing so, it also ensures there is no data loss through event tracking and necessary replays and retries.
Walmart is quietly preparing to enter the metaverse
Walmart appears to be venturing into the metaverse with plans to create its own cryptocurrency and collection of non-fungible tokens, or NFTs. The big-box retailer filed several new trademarks late last month that indicate its intent to make and sell virtual goods, including electronics, home decorations, toys, sporting goods and personal care products. In a separate filing, Walmart said it would offer users a virtual currency, as well as NFTs.
Predicting Defrost in Refrigeration Cases at Walmart using Fourier Transform
As the largest grocer in the United States, Walmart has a massive assembly of supermarket refrigeration systems in its stores across the country. Food quality is an essential part of our customer experience and Walmart spends a considerable amount annually on maintenance of its vast portfolio of refrigeration systems. In an effort to improve the overall maintenance practices, we use preventative and proactive maintenance strategies. We at Walmart Global Tech use IoT data and build algorithms to study and proactively detect anomalous events in refrigeration systems at Walmart.
Forecast Anomalies in Refrigeration with PySpark & Sensor-data
A refrigeration has four important components: Compressor, Condenser Fan, Evaporator Fan & Expansion Valve. Loosely speaking, together they try to keep the pressure at a reasonable level so as to maintain the temperature within (Remember, PV = nRT). In Walmart, we collect sensor data for all of these components (eg. pressure, fan speed, temperature) at a 10 minutes interval along with metrics like if the system is in defrost or not, compressor is locked out or not etc. We also capture outside air temperature as it impacts the condenser fan speed and in turn, the temperature.
The objective is to minimize the number of malfunctions and suggest probable resolutions of the same to save time. So, we leveraged this telemetry information in order to forecast anomalies in temperature, which would help in prioritizing issues and be proactive rather than reactive.
Walmart’s Massive Investment In A Supply Chain Transformation
Delivering many items ordered online quickly depends upon shorter lead times and the ability to support a variety of fulfillment options such as curbside pickup or ship from store. Distribution centers that traditionally just replenished a given set of stores will be increasingly asked to also fulfill ecommerce orders. Mid-mile and last mile transportation capabilities need to be improved. “That is a steep ask for any supply chain,” Mr. Guggina stated.
This is where Walmart seeks more “precision.” The use of demand management, inventory optimization, and replenishment applications can help this retail behemoth achieve much better inventory placement and fulfillment flexibility. Investing in supply chain applications also, Mr. Guggina asserts, helps them with their “relentless cost focus.”
Walmart is reducing packaging waste by right sizing packaging; for some products packaging might not be required at all. This initiative requires capturing product dimensions and other product attributes with higher accuracy. The packaging algorithms do not work if this data is not up to date.
In their distribution centers, Walmart is modernizing their warehouse management system (WMS). The system, which will launch later this year, will have better labor planning, as well as providing better inventory control.
Walmart is making extensive investments in warehouse automation. The company has deployed autonomous mobile robots for moving pallets. The retailer is also investing in the use of automation for picking/putting to and from containers. There are large investments in sortation equipment; sortation systems automatically sort products down the correct shute as they move through a warehouse on a conveyor. When it comes to these projects, warehouse control systems are used to interconnect the automation assets – the hardware - with the warehouse management system software.
Investment is being made in a highly automated warehousing solution from Witron surrounding produce. Vegetables and fruits will be able to be delivered more quickly and cheaply as a result.
Walmart Is Pulling Plug on More Robots
The retailer is phasing out the hulking automated pickup towers that were erected in more than 1,500 stores to dispense online orders. The decision reflects a growing focus on curbside pickup services that have become more popular during the Covid-19 pandemic and continues a broader retreat from some initiatives to use highly visible automation in stores.
What Walmart learned from its machine learning deployment
As more businesses turn to automation to realize business value, retail’s wide variety of ML use cases can provide insights into how to overcome challenges associated with the technology. The goal should be trying to solve a problem by using ML as a tool to get there, Kamdar said.
For example, Walmart uses a ML model to optimize the timing and pricing of markdowns, and to examine real estate data to find places to cut costs, according to executives on an earnings call in February.
Advantages of Migrating to Cloud for Enterprise Analytics Environment
We are a data team. We spend the bulk of our efforts building out data pipelines from operational systems into our Decision Support infrastructure. We synthesize the analytical data assets from operational data flow and publish these assets for consumption across the enterprise. Our ETL pipelines are built using an in-house ETL framework with workflows that run on Map Reduce and tuned with TEZ parameters and some workloads using Apache Spark. Data flows through a series of logical stages from various sources across the organization into a “Raw Zone”,” Cleansed”, and “Transformed” to build multiple fact tables suitable for the Enterprise team’s use-cases. The data is then flattened and loaded to the consumption layers for ease of business analysis and reporting. These works might be common among most of the companies today, and we hope that our story about overcoming a series of challenges through a cloud migration resonates with you and your teams.
A Markov Chain Formulation for the Grocery Item Picking Process
A major chunk of Walmart business (and most of its markets outside the US) comes from Grocery. Customers place orders online which are then delivered to the shipping address or collected by customers from the store (CnC).
What is common to both modes of fulfillment of an order?
It is the process of picking items done by associates in the store. While the actual process has many complexities like downloading of online orders into the store, figuring out locations of items in store, generation of substitutes, generating optimized number of containers to fulfil an order, generating optimized pickwalks for associates across the store etc., the basic operation performed by the associate is to look at different items in an order (typically between 50–70 items) and add them to the containers.
The case of the missing toilet paper: How the coronavirus exposed U.S. supply chain flaws
Before executives at consumer-goods giant Kimberly-Clark rushed to shut their offices on Friday the 13th of March, they convened for one last emergency meeting. Commuting home that final time, Arist Mastorides, president of family care for North America, stopped at his local Walmart, on the edge of Lake Winnebago in Neenah, Wis., to see the emergency firsthand. Mastorides oversees toilet paper brands like Cottonelle and Scott, but that evening he could find none of his own products. “A long gondola shelf that’s completely empty of bathroom and facial tissue, I never in my life thought I would ever see that,” he says. “That’s a very unsettling thing.”
The algorithms big companies use to manage their supply chains don’t work during pandemics
Even during a pandemic, Walmart’s supply chain managers have to make sure stores and warehouses are stocked with the things customers want and need. COVID-19, though, has thrown off the digital program that helps them predict how many diapers and garden hoses they need to keep on the shelves.
Normally, the system can reliably analyze things like inventory levels, historical purchasing trends, and discounts to recommend how much of a product to order. During the worldwide disruption caused by the COVID-19 pandemic, the program’s recommendations are changing more frequently. “It’s become more dynamic, and the frequency we’re looking at it has increased,” a Walmart supply chain manager, who asked not to be named because he didn’t have permission to speak to the media, told The Verge.