This sound is generated automatically. Please let us know if you have any feedback.
Scotts Miracle-Gro uses machine learning and artificial intelligence to improve inventory management through more accurate demand forecasting.
The effort was spurred by an increase in non-sustainable inventory in the wake of the COVID-19 pandemic. Demand increased during the crisis, prompting the lawn and garden care brand to exponentially expand its manufacturing and distribution footprint. At its post-pandemic peak, the company operated 18 distribution centers, president and CEO Nate Baxter told Supply Chain Dive.
However, when demand normalizes in 2023, Scotts Miracle-Gro will need to strategically size its inventory operations, Baxter said. At the time, Scotts Miracle-Gro carried $1.3 billion in inventory.
“When the demand ended, we were faced with a balance sheet that was not healthy in terms of capital allocation,” said the company’s CEO. So, our first attempt was how do we reduce the inventory we have on hand?
With the help of data analysis and predictive modeling, The company has since reduced its inventory to $625 million in 2025.. Baxter said the company will likely end up under $500 million by the end of the year.
The company has also reduced its distribution center footprint to five sites, but such a reduction was not easy. To execute effectively, the company needed the business planning side to become smarter, Baxter said.
“And the other thing I’ve noticed anecdotally is that with such a wide distribution network, it’s very easy for your supply chain people to just build inventory and put it on the network,” he said. “And the problem is, if you don’t have good planning tools, you don’t necessarily know where the demand is.”
Previously, Scotts Miracle-Gro based its inventory planning strategy on comparisons with national averages. However, according to Baxter, because different regions have different levels of demand, this method did not work.
Using machine learning algorithms on already visible inventory levels at retail partners, Scotts Miracle-Gro captured individual store data down to the SKU level to create better planning capabilities, Baxter said. From there, the company began building a machine learning model that could predict where and when inventory would be needed.
“Without implementing machine learning — and now we’re putting AI on top of that to help make better predictive decisions about inventory — it was really hard to get where the inventory needed to be,” Baxter said.
When he started building the model, Scotts Miracle-Gro was “still completely managing things in spreadsheets,” Baxter said, creating the need to use that information with the new technology. To build this model, Scotts Miracle-Gro also had to validate the data sources in a dataset.
Baxter said the next step was to enter the approved data with a planning software provider. Scotts Miracle-Gro also recently signed an agreement with a third party to integrate its machine learning model into a planning tool. Baxter did not provide details about the partner company.
Scotts Miracle-Gro plans to integrate the tool into a new ERP system that could incorporate artificial intelligence components, Baxter said.
Baxter said that while Scotts Miracle-Gro plans to continue developing internal tools, the brand is now embarking on a larger transformation to “complete this journey” with software partners such as Kinaxis and Sierra.AI.
The company also plans to continue scaling up and piloting new technology in its supply chain.
A year ago, Baxter challenged its supply chain team to take $150 million out of its supply chain over a three-year period through technology projects. Inventory management has been a big part of this effort, with the company also exploring the use of inventory drones and automated forklifts. So far, the team has achieved savings of $75 million by 2025, and the company anticipates reaching a goal of $150 million by fiscal 2027.
This story was first published in our weekly Ops newsletter. Register here
About the Author
