David Woollard is the Chief Technology Officer (CTO) at Standard AI. He’s a tech industry veteran with over 20 years of experience, having worked at firms like Samsung and NASA, and as an entrepreneur at each early and late-stage startups. He holds a PhD in Computer Science, specializing in software architectures for high-performance computing.
Standard AI offers provide unprecedented precision insights into shopper behavior, product performance, and store operations.
Are you able to share your journey from working at NASA’s Jet Propulsion Laboratory to becoming the CTO of Standard AI?
Once I was at The Jet Propulsion Laboratory, my work focused totally on large scale data management for NASA missions. I set to work with incredible scientists and engineers, learning about easy methods to conduct research from outer space. Not only did I learn quite a bit about data science, but additionally large-scale engineering project management, balancing risk and error budgets, and large-scale software systems design. My PhD work on the University of Southern California was in the realm of software architectures for prime performance computing, and I used to be in a position to see the appliance of that research first-hand.
While I learned an incredible amount from my time there, I also really desired to work on things that were more tangible to on a regular basis people. Once I left JPL, I joined a friend who was founding a startup within the streaming video space as one in every of the primary hires. I used to be hooked from the start on constructing consumer experiences and startups generally, each of which felt like a break from my previous world. Once I got a probability to affix Standard, I used to be drawn to the mixture of hard scientific problems in AI and Computer Vision that I loved in my early profession with tangible consumer experiences I discovered most fulfilling.
What motivated the shift in Standard AI’s focus from autonomous checkout solutions to broader retail AI applications?
Standard AI was founded seven years ago with the mission to bring autonomous checkout to market. While we succeeded in delivering the best-in-class computer vision only solution to autonomous checkout and launched autonomous stores, ultimately we found that user adoption was slower than anticipated and consequently, the return on investment wasn’t there for retailers.
At the identical time, we realized that there have been quite a few problems the retailer experienced that we could solve through the identical underlying technology. This renewed concentrate on operational insights and enhancements allowed Standard to deliver a more direct ROI to retailers who’re searching for opportunities to enhance their efficiencies to be able to offset the consequences of inflation and increased labor costs.
How does Standard AI’s computer vision technology track customer interactions with such high accuracy without using facial recognition?
Standard’s VISION platform is designed to trace shoppers in real space by analyzing video from overhead cameras in the shop, distinguishing between humans and other elements in each video, and estimating the pose, or skeletal structure, of every human. By searching through multiple cameras at the identical time, we will reconstruct a 3D understanding of the space, similar to we do with our two eyes. Because now we have very precise measurements of every camera’s position, we will reconstruct a consumer’s position, orientation, and even hand placement, with high accuracy. Combined with advanced mapping algorithms, we will determine shopper movement and product interaction with 99% accuracy.
How does Standard AI make sure the privacy of shoppers while collecting and analyzing data?
Unlike other tracking systems that use facial recognition to discover shoppers between two different video streams, when Standard is determining a consumer’s pose, we are only using structural information and spatial geometry. At no time does Standard’s tracking system depend on shopper biometrics that will be used for identification like the patron’s face. In other words, we don’t know who a consumer is, we just know the way shoppers are moving through the shop.
What are a few of the most important insights retailers can gain from using Standard AI’s VISION platform?
Retailers can gain quite a few insights using Stand’s VISION platform. Most importantly, retailers are in a position to get a greater understanding of how shoppers are moving through their space and interacting with products. While other solutions give a basic understanding of traffic volume through a selected portion of a store, Standard records every shopper’s individual path and may distinguish between shoppers and store employees to present a greater accounting of not only traffic and dwell, but the particular behaviors of shoppers which might be buying products.
Moreover, Standard can understand when products are out of stock on the shelf and more broadly, shelf conditions like missing facings that impact not only the flexibility of the patron to buy products, but to form impressions on different brand offerings. Such a conversion and impression data is precious to each the retailer and to consumer packaged goods manufacturers. This data simply hasn’t been available before, and carries big implications for improving operations on every little thing from merchandising and marketing to provide chain and shrink.
How can predictive insights from VISION transform marketing and merchandising strategies for retailers?
Because Standard creates a full digital replica of a store, including each the physical space (like shelf placements) and shopper movements, now we have a wealthy data set from which to construct predictive models each to simulate store movement given physical changes (like merchandising updates and resets) in addition to predicting shopper interactions based on their movement through the shop. These predictive models allow retailers to experiment with–and validate–merchandising changes to the shop without having to take a position in costly physical updates and long periods of in-store experimentation. Further, impressions of product performance and interaction can inform placement on the shelf or endcaps. Altogether these may also help prioritize spend and drive greater returns.
Could you provide examples of how real-time offers based on predicted customer paths have impacted sales in pilot tests?
While Standard doesn’t construct the actual promotional systems utilized by retailers, we will use our understanding of purchaser movement and our predictions of product interactions to assist retailers understand a consumer’s intent, allowing the retailer to supply deeply meaningful and timely promotions relatively than general offerings or only recommendations based on past purchases. Recommendations based on in-store behaviors allow for seasonality, availability, and intent, all of which translate to simpler promotional lift.
What were the outcomes of the tobacco tracking pilot, and the way did it influence the brands involved?
Inside a day of operating a pilot of 1 retailer, we were in a position to detect theft of tobacco products and flag that back to the retail for corrective actions. Long term, now we have been in a position to work with retailers to detect not only physical theft but additionally promotion abuse and compliance issues, each of that are very impactful to not only the retailer but to tobacco brands that each fund these promotions and spend significant resources on ensuring compliance manually. For instance, we were also in a position to observe what happens when a customer’s first selection is out of stock; half of shoppers selected one other family product, but nearly 1 / 4 purchased nothing. That’s potentially a variety of lost revenue that may very well be addressed if caught sooner. Because our VISION platform is all the time on, it’s turn into an extension of tobacco brands’ sales teams, in a position to see (and alert on) the present state of any store in the entire or a retailer’s fleet at any time.
What are the largest challenges you’ve faced in implementing AI solutions in physical retail, and the way have you ever overcome them?
Working in retail environments has include quite a few challenges. Not only did now we have to develop systems that were robust to issues which might be common within the physical world (like camera drift, store changes, and hardware failures), we also developed processes that were compatible with retail operations. For instance, with the recent Summer Olympics, many CPGs modified their packaging to advertise Paris 2024. Because we visually discover SKUs based on their packaging, this meant we needed to develop systems able to flagging and handling these packaging changes.
From the start, Standard has chosen technical implementations that will work with retailer’s existing processes relatively than change existing processes to satisfy our requirements. Store’s using our VISION platform operate similar to they did before with none changes to physical merchandising or complex and expensive physical retrofits (like introducing shelf-sensors).
How do you see the role of AI evolving within the retail sector over the following decade?
I believe that we’re only scratching the surface of the digital transformation that AI will power inside retailers in the approaching years. While AI today is essentially synonymous with large language models and retailers are interested by their AI strategy, we imagine that AI will, within the near future, be a foundational enabling technology relatively than a technique in its own right. Systems like Standard’s VISION Platform unlock unprecedented insights for retailers and permit them to unlock the wealthy information within the video they’re already capturing. The kinds of operational improvements we will deliver will form the backbone of shops’ strategies for improving their operational efficiency and improving their margin without having to pass costs onto consumers.
