• Retailers like Target and Walmart use AI to prevent stockouts and manage inventory.
• AI systems can predict demand to help improve inventory accuracy and availability.
• This article is part of "How AI Is Changing Everything: Supply Chain," a series on innovations in logistics.

The adage "too much, too little, just right" isn't just for Goldilocks and her porridge. Balance is also critical in inventory management, the part of the supply chain responsible for analyzing what consumers will buy and making sure products are in stock at the right place and the right time.

Excess inventory can lead to markdowns or expired goods, but too little product can lead to shortages that impact a retailer's brand image, customer satisfaction, and bottom line.

To prevent inventory from running out, big-box retailers such as Target, The Home Depot, and Walmart are using AI to predict when product amounts could dwindle. As a result, Target's inventory availability has improved every year for the last four years, Prat Vemana, the executive vice president and chief information and product officer at Target, told Business Insider.

AI can help retailers proactively adjust stock before disruption strikes rather than reacting to changing conditions, said Ajoy Krishnamoorthy, the CEO of inventory-management platform Cin7. That's especially critical today, Krishnamoorthy added, when factors like consumer behavior, inflation, and trade policy constantly impact supply chains.

"AI thrives in this environment," Krishnamoorthy said.

From old methods to AI

Traditionally, companies procure inventory, manage logistics, and analyze consumer behavior in silos, said Vidya Mani, an associate professor of business administration focused on technology and operations management at the University of Virginia. Teams do individual research, then come together to develop a strategy and execute it.

"We no longer have that time," Mani said. "By the time you finish doing it, the world will have changed on you."

Before Target started using AI to predict stockouts, the retailer relied on software-based applications, which didn't react or adapt to real-world changes as quickly as AI systems, according to Vemana. In fact, Target said in a blog post that it previously failed to catch half of its products that were out of stock because the technology they used thought that inventory existed when it actually didn't.

Target changed how it managed inventory in 2023 with the introduction of Inventory Ledger, an internal tech system that tracks inventory changes across stores and uses AI to predict when products might be out of stock "even before it's obvious to team members or systems," Vemana said.

Today, Target uses AI-driven inventory management for more than 40% of its product assortment, which is more than double when it started two years ago, Vemana said.

With Inventory Ledger, algorithms pull in data like supply lead times, transportation costs, current inventory, and consumer demand. Some models are more accurate for frequently purchased categories, and others are better suited to discretionary purchases or clearance items, so Target uses both kinds. There are also models that detect items that are in the store but in the wrong aisle or shelf, Vemana said.

Target has a demand forecasting tool that "makes billions of predictions each week about how many units of each item we'll need in stores and online," Vemana said. Together, all of these technologies guide employees' decisions about when, where, and how to reorder products and replenish stock.

"Combining traditional software with AI helps us make smarter, faster decisions about inventory management and keep our stores stocked more consistently," Vemana said.

One of Cin7's customers, ABC School Supplies, is also using AI to access real-time sales data, potential stock shortages, and supplier lead times, so it can "reorder proactively and avoid costly gaps in supply," Krishnamoorthy said.

The AI-driven inventory management marks a big change from what ABC School Supplies did in the past. It used to copy and paste website orders into its system, make a pick-and-pack list on paper, walk that physical list over to the warehouse, and manually update inventory, Krishnamoorthy said

The Home Depot is also taking an AI-based approach to inventory. In 2023, the retailer rolled out a machine-learning-powered app called Sidekick, which guides store workers to restock shelves and find products on overhead shelves, among other features.

"It helps make sure products are on shelves for our customers, and it manages our on-hand accuracy, which feeds to our replenishment and selling platforms," a spokesperson for The Home Depot said.

AI's predictive power for inventory planning

Krishnamoorthy said that in retail, "AI is exploding" as businesses move away from static planning to dynamic forecasts that anticipate demand and prevent stockouts.

AI allows businesses to get more granular with their inventory data, avoiding stockouts at particular store locations or during peak times. Mani gave the example of cosmetics and how different stores will have varying product needs based on consumer demographics.

"AI can figure out those patterns of baskets that are bought frequently in these different clusters," Mani said. "You don't need to feed it that contextual information."

Target is also working on technology that predicts which colors and sizes of seasonal items will sell, so it can stock those items in specific stores "to meet local demand," Vemana said.

At Walmart, AI-based inventory management systems use algorithms to make sure stores in warmer states have the right amount of pool toys and colder states stock enough sweaters, according to a press release on the company's website. If a particular item isn't selling on the East Coast but it's flying off shelves in the Midwest, algorithms flag that pattern so Walmart can reposition its inventory.

As retailers continue to develop and deploy AI tools, Mani predicts the technology's use cases will advance over the next decade.

Mani said that in two to three years, AI will likely flag stockouts without a person needing to walk into a store to confirm. Five years out, AI could automatically reorder inventory when algorithms detect that stock is running low. And in 10 years, AI would understand how macroeconomic events (like inflation) will change future consumer purchase behavior patterns and adjust inventory plans accordingly.

"It will feed it into your rulemaking rather than reacting to the situation," Mani said. "You'll be living in a different world."

• Albert Invent is a digital platform that uses AI-driven analysis to assist chemists with research.
• The platform integrates data from electronic lab notebooks to speed up product development.
• This article is part of "How AI Is Changing Everything: Supply Chain," a series on innovations in logistics.

Cosmetic chemistry, or the science of making beauty products, is a complex process that requires understanding how ingredients interact with each other and with the skin.

With so many variables to consider — safety, shelf lifespan, texture, and appearance — the process of blending ingredients for face creams, eye shadows, lipsticks, and other cosmetics can be time-consuming for chemists, who typically conduct independent research to figure out which compounds and minerals can work together to create a safe, effective, and sellable product.

Albert Invent, based in Oakland, California, seeks to simplify this process for chemists with its digital platform called Albert.

The company's CEO, Nick Talken, said Albert enables chemists to research and develop safe, high-performing products without the need to refer to the notebooks and spreadsheets where they typically store data. Since Albert integrates data that's already been stored in electronic lab notebooks and laboratory information management systems, chemists can come up with test-worthy formulations in less time.

How AI can help chemists develop safe and effective cosmetics

Albert is trained on more than 15 million molecular structures, Talken said. When chemists — from companies like the adhesive and cleaning supplies manufacturer Henkel, the Teflon-maker Chemours, and the chemical manufacturing company Nouryon — use the platform, they can look up which permutations of molecules will work best to achieve a specific goal.

The platform was designed to capture the kind of information that chemists typically track in notebooks or on spreadsheets, such as the materials and substances they might use, their compositions, and processing steps.

When a chemist asks Albert for input on which other substances work well with a particular ingredient, the system offers feedback on possible substance combinations and predicts the physical, toxicological, and visual properties of new compounds before they are synthesized in a lab. This AI-driven analysis gives formulators the opportunity to determine whether a concoction is safe and effective to produce, or whether they should scrap the idea, in minutes.

Albert Invent partnered with Nouryon, which owns a collection of formulation strategies for the personal care industry (think cosmetics, hair care, and skincare products) that have been cleared as effective and safe. The result: a digital platform for developing new cosmetics formulations, called BeautyCreations.

Instead of employing the traditional product-development methods of trial and error and real-time experimentation — methods that can typically take anywhere from four to six weeks — Nouryon's chemists can use BeautyCreations to look through the company's existing formulations for hair and skincare products and filter for results that match their desired safety standards and marketing claims, all while adhering to stringent development timelines.

David Freidinger, the vice president of personal care and pharma at Nouryon, said this technology has enabled the company's chemists to develop new products from almost anywhere in the world. It's also improved the speed and quality of Nouryon's internal product development, as the company can look at BeautyCreations data to better understand market trends and prioritize development initiatives accordingly.

An AI tool for chemistry beyond cosmetics

Arthur Tisi, a former CTO and chief information officer who advises private equity and portfolio companies on digital technology strategies, said that the molecular AI technology behind Albert could be of use to other data-heavy industries in the future.

"The ability to 'digitalize' our technical expertise and make it available to customers 24/7 enables accelerated scaling and efficiency in customer support," Tisi wrote in a recent email to BI. He added that tools like Albert are powerful because they offer both product-formula data and consumer insights.

Tisi said that in the future, the value of molecular AI will go beyond its speed benefits. He said that this technology has the potential to uncover certain chemical formulations that scientists might miss.

Freidinger said industries that use reams of empirical data to create products or deliver services could benefit from AI tools like Albert to improve speed and quality.

"The same technology that speeds up skincare development can revolutionize personalized medicine, where rapidly identifying the perfect molecular combinations could mean delivering custom-targeted therapies for individual patients, potentially turning fatal diagnoses into manageable conditions," Freidinger said.

Meanwhile, Talken said that Albert has the potential to be used for inventing new polymers and batteries.

• Hospitals face frequent disruptions in inventory for supplies like IV fluids and medications.
• Mayo Clinic, Cleveland Clinic, and Rush University Medical Center leaders talk about managing that with AI.
• This article is part of "How AI Is Changing Everything: Supply Chain," a series on innovations in logistics.

When Hurricane Helene hit North Carolina in late September, it caused more than $59 billion in damages.

Among those businesses damaged was one of the US's main manufacturers of IV fluids, used to rehydrate patients and give them medicine. The resultant shortage forced hospitals to conserve and reduce their use of IV fluids, which led to canceled surgeries and treatment delays.

Such disruptions to hospital inventory have long been hard to predict and difficult for hospitals to navigate. At the same time, keeping too much of a given item on hand is wasteful. In 2019, hospitals spent about $25.7 billion on supplies that they didn't need, the consulting firm Navigant found in a study of over 2,100 hospitals — about $12.1 million for an average hospital.

To reduce waste, while ensuring providers have the medical supplies they need, some leading hospital systems are using automation, predictive analytics, and other forms of artificial intelligence to manage inventory.

Business Insider asked supply chain managers from three systems — the Cleveland Clinic, the Mayo Clinic, and Rush University Medical Center — about how they use machine learning, generative AI, sensors, and robotics to anticipate shortages and help with contracting and ordering.

The following has been edited for length and clarity.

Business Insider: What are some of the most effective and innovative ways that you're making use of AI?

Joe Dudas, Mayo Clinic's division chair of supply chain strategy: We've deployed autonomous delivery and robotic warehouse fulfilment — robots that pick orders.

We're advancing our algorithms for auto-replenishment to be even more accurate. We're also using AI to explore savings opportunities and understand the sustainability of those opportunities over the length of an agreement, based, for example, on demand.

We're doing advanced analytics in high-spend categories — we're just getting a lot smarter about what's happening with a little bit more precision. Even our expense management, we're looking at profit and loss, and supply expense, to understand what's happening from a budgetary perspective. Based on the present and what's happened in the past, we can look forward with some degree of accuracy.

Geoff Gates, Cleveland Clinic's senior director of supply chain management: In some of our tools, instead of having someone click lots of buttons and type data into 20 or more fields, for example, we have been able to automate that process with AI, which saves employees 20 minutes every time. Those are the tasks that are the biggest benefit from a pure efficiency standpoint — they let people focus on other things.

We also use AI for document recognition and have been using it to manage invoices through our ERP inventory-management system for the last four years. If a medical-supply rep has a bill sheet that needs to get processed — to create a purchase order — the rep submits it, and our tool automatically creates a requisition.

With distribution, our goal is to create a better view of what we have within our health system and the hospital. Our goal with key suppliers is to be able to see which supplies they have in their warehouses and to predict disruptions. For instance, if we can see that a supplier doesn't have a shipment coming in, the system would alert us that we'll have a problem in two weeks.

Jeremy Strong, Rush University Medical Center's vice president of supply chain: For inventory management, we have weighted bin systems in all heavy-volume areas. When a nurse takes something out and puts something back in, we know it.

Once we implemented that, we could start to be proactive. We have a system that includes our distributor's data about inventory coming into their distribution center. They can see where our utilization patterns are changing. Then AI reviews all that. A back-order dashboard creates alerts when automatic supply-refill levels across the system are low, inventory is low at the distribution center, or shipments from manufacturers are taking longer than anticipated. We can anticipate that we're going to run out in a week from now or going to have a back-order problem.

We also use it in contract management. When a contract is loaded in, AI will send it to the category manager with a summary and potential clauses to review. It can also automatically send contracts to the cybersecurity team for approval. If it has patient information, it sends it to the risk lawyers. If it has indemnification, it sends it to our regular lawyers.

What are some of the advantages of automation that your system has realized?

Dudas: Our automation gives us agility. We can see things sooner and adjust faster because of our technology but also because of our talent.

Somebody asked me the other day, "Where are you advancing?" I said, "We're not advancing. We're keeping up with all of the curveballs we get thrown on a day-to-day basis."

Gates: At this point, the tools have touched almost everyone in the supply chain. Even a specific process that only impacts one or two people who were doing those tasks allows us to be more efficient and accurate.

Strong: The goal was to move from being reactive and putting out fires to being more predictive, to prevent fires from happening, see things ahead of time, and be more efficient.

We've also sped up contract review. We cut the time it takes to review them in half and more than doubled the number of reviews each contract gets.

What advice do you have for other companies interested in implementing AI to streamline inventory?

Dudas: Recognize that you can't do everything yourself. Even as big as our organization is, it's not big enough. Scale is your friend in the supply chain.

Gates: Some things weren't necessarily the biggest opportunities to start with, but they were low-risk processes that gave us the skillset needed to leverage AI.

We're most focused on finding the right solution for the problem rather than forcing a solution.

Strong: The best tasks or processes to tackle are ones that are repetitive or require pulling and summarizing data from multiple digital sources. Tackle these, and you can gain efficiencies, improve productivity, and be proactive.