Nike to marry predictive analytics and RFID to optimize inventory performance

Photo: Nike
Aug 12, 2019
Tom Ryan

Nike Inc. has acquired Celect, a predictive analytics firm founded by MIT professors, to accelerate its ability to match inventories to consumer needs.

Celect’s cloud-based analytics platform allows retailers to optimize inventory across an omnichannel environment through hyper-local demand predictions. Celect’s team will be integrated into Nike’s operations. Its co-founders will continue as tenured professors at MIT, consulting Nike on an ongoing basis.

“As demand for our product grows, we must be insight-driven, data optimized and hyper-focused on consumer behavior,” said Eric Sprunk, Nike’s COO, in a statement. “This is how we serve consumers more personally at scale.”

In a column for Retail Touchpoints from July, Andrea Morgan-Vandome, Celect’s chief marketing officer, wrote that advancements in artificial intelligence and machine learning now provide retailers with a more accurate view of demand across channels to choose the best fulfillment strategy based on product availability, likely demand, capacity constraints, shipping costs, delivery timing and other factors.

At the store level, such insights would reveal that a location seeing high inventory turnover wouldn’t be able to cover walk-in demand if it was also fulfilling online orders. Vice versa, a store seeing slower turnover risks becoming overstocked if it didn’t support online orders.

She wrote, “For each fulfillment decision that needs to be made, advanced optimization can account for the overall margin profitability and customer satisfaction by identifying the immediate payoff versus the long-term opportunity cost — instantly.” 

The Celect purchase builds on Nike’s acquisition in March 2018 of Zodiac, another predictive analytics platform that forecasts the behavior and lifetime value of individual customers and customer segments. 

On its fourth-quarter conference call, Nike revealed that it will begin to use RFID across footwear and non-licensed apparel this fall at stores to “dramatically improve” inventory visibility, accuracy and ultimately drive quicker in-store fulfillment.

Mark Parker, Nike’s CEO, told analysts, “RFID gives us the most complete view of our inventory that we’ve ever had. It’s quickly becoming the most precise tool in our arsenal, to meet an individual consumer’s specific need at the exact right moment.”

DISCUSSION QUESTIONS: How will the Celect acquisition benefit Nike? Is marrying predictive analytics and RFID a strategy that will become a competitive necessity for big retail chains?

Please practice The RetailWire Golden Rule when submitting your comments.
"These investments in big data tech are well-timed for Nike to gain a competitive edge this holiday season. "
"Knowing who your customers are and when they will need product and being proactive in that is what retailing is all about and will be in the near future."
"Nike, like no other brand, knows their customer; this supports that. This is a perfect union that will more perfectly align demand forecasts to supply."

Join the Discussion!

19 Comments on "Nike to marry predictive analytics and RFID to optimize inventory performance"

Sort by:   newest | oldest | most voted
Mark Ryski

Matching inventory to consumer demand is critical to reducing out-of-stocks and improving in-store conversion rates. Using RFID to improve inventory tracking and using predicative analytics to allocate product at the micro-market level is a smart and practical application of these technologies that substantially already exist. By aquiring Celect, Nike is demonstrating how important it believes this capability is for their future. When well executed, this approach could benefit any retailer.

Ken Lonyai

In theory, this is absolutely the way to go and the future of effective inventory/merchandising, so in time it will be interesting to see how well this works.

And yes, RFID is a necessary component of real-time inventory management.

Rob Gallo

Definitely a positive move for Nike. Having products in the right place, right time and right amount is the goal and this helps get them there. RFID will be a big benefit for Nike and other companies that can make the cost/benefit work whether it’s at the item, case or pallet level. Look for other large companies to begin buying such integral solutions versus being customers.

Brandon Rael

Retail merchandising magic is all about the blending of the arts and sciences to drive outstanding customer experiences. Acquiring Celect is a step in the right direction to enable Nike to provide more prescriptive experiences, that are fueled by RFID inventory insights, as well as predictive analytics.

However, the science part of the equation has to be equally matched by the right products and merchandising drops that will meet the needs of Nike’s extremely loyal customer base. Ultimately it will come down to the execution side, especially when the Nike customer is navigating across and shopping in multiple channels.

David Naumann

It was interesting to hear that Nike acquired Celect instead of just contracting with the company to deploy its software and services. There are some brilliant minds at Celect and it appears that Nike wanted to infuse this talent into their team. Assuming that Nike plans to keep this AI expertise all for its own use, which is not clear, this would allow them to direct the development for their specific needs and keep it out of the hands of their competitors.

Marrying the predictive analytics with RFID is another huge step in dramatically improving the accuracy of inventory visibility. This combination will enable Nike to make much smarter fulfillment decisions in real-time.

Jeff Sward

Simple concept that takes a lot of brain power to execute. Fill the order from the location with the highest weeks of supply. Don’t let the location with the lowest weeks of supply run out of inventory. Don’t let inventory sitting in one stockroom turn into markdowns while selling out in another location. Maximize both sales and margin. Smart. Overdue. Underutilized.

David Dorf
5 months 16 days ago

The nice thing about machine learning is that it gets more accurate over time because it’s seeing more and more data. And of course RFID provides tons of data. All retailers should be looking at ML technology to improve forecasting accuracy and improve the supply chain. But I find it odd that Nike bought Celect instead of just using its products. They must want something very custom that is beyond what the current product delivers.

Ron Margulis

Joe Andraski and the folks at the VICS Item Level RFID Initiative were working on this nearly a decade ago and making very good headway (Disclaimer: My agency supported the marketing effort for VICS). Things seemed to slow down as retailers and manufacturers started to keep successes and failures much closer to the vest. It’s good to see Nike and its partners hopefully jumpstart the initiative.

Lisa Goller

These investments in big data tech are well-timed for Nike to gain a competitive edge this holiday season.

Predictive analytics will help Nike personalize its offerings and more accurately anticipate what consumers will buy. Benefits include better decision-making for forecasting, assortment strategy, marketing, and lower returns and shipment costs.

Meanwhile, tagging and tracking inventory across the supply chain using RFID will improve transparency, inventory management, loss prevention and efficiency, helping to serve shoppers with greater agility.

Both data-driven technologies will become more common among retail chains as consumers demand more personalized, prompt service.

Frank Riso

The acquisition of Celect will benefit Nike as the next big step in AI for the shoe retailer. Knowing who your customers are and when they will need product and being proactive in that is what retailing is all about and will be in the near future. This speaks to the individual need as opposed to a general need. RFID is the best way to maintain the inventory picture up to the minute without the need for many hours of labor and therefore meeting the needs of the customer is a proven benefit of RFID. RFID will play a significant role if it doesn’t already in fashion retail.

Ken Morris
Ken Morris
Retail industry thought leader
5 months 16 days ago

Predictive analytics help retailers make smarter product decisions and offer more personalized experiences. Furthermore, it can act as the catalyst to encourage proactive, rather than reactive, retail actions in real-time. And RFID is a key to inventory visibility and management, allowing retailers to easily view current inventory to make for more accurate stock counts, help with loss prevention and eliminate the need to carry safety stock. Combining predictive analytics with RFID is key to improving the accuracy of inventory visibility and ensuring that products are in the right place to fulfill customer needs and offer more effective fulfillment options. This combination should give Nike an advantage by allowing them to have real-time inventory management.

Shawn Harris

Nike, like no other brand, knows their customer; this supports that. This is a perfect union that will more perfectly align demand forecasts to supply.

Harley Feldman

Celect will provide Nike with a better analysis of the customer demand for the items in each store allowing the store manager to be more accurate in replenishment ordering. In order to provide a more accurate picture of the store inventory for the Celect models, Nike will be using RFID in the stores. RFID will provide a quicker and more accurate method for the associates to take store inventory.

Zach Zalowitz

A definitive “YES” is the answer. This is a current edge that will absolutely become a competitive necessity, however RFID still continues to lag as fully adopted technology in part due to cost. I’ve been seeing a lot of players in this space. Onera is another company making waves, where the optimal inventory and inventory protection levels are calculated in real-time to ensure proper distribution of inventory to its greatest need. I see more of the use cases in taking “stale” store inventory and shipping it via ship-from-store, but that’s a byproduct of planning. The real gold is going further upstream to distribute the inventory quicker to the best place, up-front, before it goes stale!

Shep Hyken

Managing inventory to ensure merchandise is available, yet at the same time not having too much, is a delicate balancing act. Sales (as in money) are lost because of out-of-stocks and money is wasted with too much inventory that moves too slow (if at all). Celect can help optimize inventory and distribution. That’s all about maximizing profitability. That’s good for everyone in the supply chain, from manufacturer to retailer to consumer.

Adrian Weidmann

Supply chain visibility and transparency yet again! So many topics and issues shared and posted through the years here on RetailWire could be addressed by knowing what retailers actually have on their shelves. Nike, for one, has apparently figured that out with both their acquisition of Celect and the use of RFID. This is what my colleague and friend Harley Feldman, would refer to as ‘small data.’ You don’t need to swim in an ocean of “big” data to drive a better customer experience for all. Knowing what your customer buys, where it’s bought and what and where your inventory actually is, is the only way brands and retailers will be able to deliver an acceptable customer experience in an omnichannel retail environment. It is mandatory to have supply chain visibility and transparency through the entire retailing journey – before, during, and after the in-store shopping experience.

Ricardo Belmar

A brilliant move by Nike to improve all areas of fulfillment and inventory management, Yes, marrying RFID and machine learning is long overdue to support both personalization efforts and eliminating out-of-stocks.

In a study by IHL Group that we supported earlier this year, they uncovered that out-of-stocks are driving up to 24% of Amazon’s retail sales across product categories. Clearly, Nike is pushing to solve this challenge via AI and ML as they continue to move towards more personalization and just plain better serving their customers.

Thinking about Nike’s House of Innovation flagship store, I can see this acquisition further driving product mix, increasing relevant personalization for customers, while ensuring the products customers want to buy in-store are there s well as for localized fulfillment via ship from store. An overall win-win for Nike and its customers.

Patricia Vekich Waldron

Interesting that Nike chose to buy (vs build or partner with) Celect. Either they want the talent or very custom capabilities to help them implement and execute.

James Tenser

Many facets to consider regarding Nike’s acquisition of Celect and it’s very cool inventory solution. Within its 1,100 owned retail locations worldwide, there is little doubt that forecasting and optimizing store-level inventory levels is highly desirable.

But Nike products are distributed through tens of thousands of other retailers. It’s not as clear to me how it will apply predictive analytics to help those distributor locations. I suppose Nike could tell those stores “here’s what our AI says you get in your next order,” retailers may have their own ideas about what their shoppers want, however.

Item-level RFID is pretty well-suited for Nike-type merchandise, and predictive analytics can be a game changer for many types of fashion and apparel products. The benefits would roll up the supply chain to influence factory order quantities and assortment decisions.

"These investments in big data tech are well-timed for Nike to gain a competitive edge this holiday season. "
"Knowing who your customers are and when they will need product and being proactive in that is what retailing is all about and will be in the near future."
"Nike, like no other brand, knows their customer; this supports that. This is a perfect union that will more perfectly align demand forecasts to supply."

Take Our Instant Poll

Do you agree that marrying predictive analytics and RFID is the future of inventory optimization?

View Results

Loading ... Loading ...