Bringing AI to inventory optimization

I don’t often interview solution providers for this column, but last week I had a call with Sivakumar Lakshmanan – Siva to Industry. Lakshmanan is the CEO of, a cloud-based software company, now part of Zebra Technologies, which provides what we called multi-level inventory optimization down to the shelf level for retailers . outlines what it provides as AI and machine learning-based inventory management and allocation solutions specific to forecasting and merchandising for the retail and CPG industries .

I was prompted to have the conversation by two factors. The first is an interview I did in September 2021 with Tom Bianculli, Chief Technology Officer of Zebra Technologies. Zebra had recently announced the acquisition of, which at the time was one of four acquisitions, including Fetch Robotics and Reflexis Systems, that took a company rooted in data collection and mobility into new areas. digital. I wanted to understand the strategy.

The second was a brief conversation I had on the booth at this year’s Gartner conference in Orlando. It was the first Gartner event since 2019, and as I walked through the exhibit hall, it was clear to me that three years in technology is a lifetime. What I’ve realized from talking to exhibitors is that there’s been a flurry of new companies, new offerings, and new approaches to supply chain planning and execution software since these last events, and I was not sure that I had understood them all or of their place. In particular, I wanted to learn more about what AI and machine learning bring to the table.

The first thing I learned was that has been around a lot longer than I thought. AI didn’t exist when it was founded nearly 10 years ago in 2013, but the idea was to create “a strong analytics company that helps retailers,” Lakshmanan said. With a $56 million investment from Goldman Sachs, acquired 5 or 6 other companies and by 2018 had gone to market as a Software as a Service (SaaS) company with multiple offerings to meet to management and inventory management. planning challenges faced by retailers and CPG companies. Three years later, was acquired by Zebra.

It’s no surprise that the company is very data-driven – the legacy of Zebra. “Our position has always been that with cloud technology and computing, more data will be available to enable better decision-making,” Lakshmanan said. “And, over the last ten years, and especially the last two years, this trend has evolved throughout the value chain. Data that wasn’t even captured before is now captured.

Examples may include weather data used by wine companies to plan their shipments to avoid excessive heat, or pollen data used by Johnson & Johnson to position ZYRTEC®. The availability of more consumer data allows companies to make better purchasing decisions when buying in 6-12 months; and the availability of better near-term data enables those same companies to be more efficient when allocating inventory between distribution centers and stores, down to shelf level. *Editor’s note: J&J is not a customer of

Lakshmanan says this has become more critical over the past two years. “Cyclical patterns in the consumer products market are nothing new,” he said. “We always had ups and downs, but they were on 3 to 5 year horizons. Companies have had time to react. This started to decline before the pandemic with omnichannel retailing coming with more complexity and more choice for consumers.

The pandemic, he added, was like the three weather systems that came together in The Perfect Storm to create one giant calamitous event. “We were already in a transition period, then all of a sudden the pattern went from too much stock to no stock, then from no demand to too much demand,” he said. “And with the volatility still present in the economy, the data is still unclear. We hear from retailers that even the wealthiest customers are not spending and other retailers say that they have high demand. the moment a retailer develops a strategy for the current environment, it has changed again.

Pursuing today’s consumer habits is a lost game, he says. “It’s important to have a long-term view so that the next time the pattern changes, you’ll be prepared,” he said.

The solution works by combining historical data that supply chains have always used as well as new data available, doing it at a scale perhaps never used before, and then using emerging technologies like AI and machine learning to process that data, make decisions, and then learn from the execution of those decisions.

“If I’m a retailer buying from CPG companies to serve hundreds of stores, I have to make inventory decisions like what port to land, what fulfillment centers to send it to, how to allocate it to stores up to ‘shelf level and at what price to sell it,” Lakshmanan explained. “Part of my data equation is knowing what sold historically, at what price, what promotions I ran, what inventory I had I and whether there were external factors, such as rain. Now, if I know it’s going to rain next week, I have back and forward data that I can run through an algorithm to determine things like likely demand at a store in Plano, TX.

If a manager doesn’t like this answer, they can relaunch it with a different promotion to see if the system predicts a different outcome. And, with improvements in cloud computing technology, it can execute those scenarios very quickly.

Similar to my interview with Tom Bianculli last year, I asked Lakshmanan to explain the synergies in Zebra’s acquisitions. “ and Reflexis are primarily in scheduling, inventory and labor management,” he said. “Zebra has always been an execution company. We believe you need to be much more responsive today, from planning to execution, and now you can put them together. Information from or Reflexis may be transmitted to a portable device; Zebra can capture data and then send it back to our engines. And, if I can go to a CPG company and say that with these solutions we can manage labor and inventory costs, you have the CEO’s attention.

About the Author

Bob Trebilcock Bob Trebilcock, Managing Editor, has covered material handling, technology, logistics and supply chain topics for nearly 30 years. In addition to Supply Chain Management Review, he is also editor of Modern Materials Handling. A graduate of Bowling Green State University, Trebilcock lives in Keene, NH. He can be reached at 603-357-0484.

Previous Indian economy stalled just short of breakout velocity
Next Elevance Health (NYSE:ELV) - What to Know About B of A Securities' Elevance Health Upgrade