How AI Is Telling Us When Golfers Are Playing: And It’s All About Cars


By Harvey Silverman, Contributor, Golf Business | Silverback Golf Marketing 

Maybe you’re driving that vintage 1971 Ford Pinto, or perhaps a 1985 Yugo, or another pre-1996 relic. If so, you would not have been tracked going to a golf course and be part of a recent study published by Stanford University titled “How Working from Home Boosted Golf.” 

We’ve done an excellent job convincing ourselves that part of why rounds have increased dramatically during the Covid era was the sudden and rapid transformation of the national workspace. “Home sweet home” became “Work sweet home” for millions of people and continues today. But the Stanford analysis reveals more precise data on when the WFH crowd plays, and the results are startling.

First, researchers Alex Finan and Nick Bloom used AI (Artificial Intelligence) to geo-locate 3400 US golf courses (I guess they hadn’t heard about the Internet Golf Database). AI used satellite imagery to easily identify the locations of golf courses by looking for long green strips, maybe some sand, along with clubhouses and parking lots. The location dispersion is typical of how we map golf courses – more east of the Rockies than west and mostly clustered around major metropolitan areas. It’s a huge sample size that validates the collected data.

They then used tracking data from Inrix, which “provides location-based data and software-as-a-service analytics — such as real-time and historical traffic conditions, road safety, and parking availability — to automakers, businesses, cities, and road authorities worldwide, as well as turn-by-turn navigation applications such as Google Waze.” (Wikipedia). Stanford used GPS and cell phone locations for 140 million car trips daily. It defined visits to golf courses as durations between two to six hours from April 2019 to November 2022 and combined that data for 3400 courses to create national figures.

So, yeah, you’re being tracked. But both the vehicle and phone GPS data are anonymized. From the report, here is how the data flows. And we thought being followed online was scary:

Once a driver gets into a car, dozens of sensors emit data points that flow to the car’s computer: The driver door is unlocked; a passenger is in the driver’s seat; the internal cabin temperature is 86 degrees Fahrenheit, the sunroof is opened; the ignition button is pressed; a trip has started from this location.

These data points are processed by the car’s computers and transmitted via cellular radio back to the car manufacturer’s servers.

As the trip continues, additional information is collected: the vehicle location and speed, whether the brakes are applied, which song is played on the entertainment system, whether the headlights are on or the oil level is low.

The data then begins its own journey from the car manufacturer to companies known as “vehicle data hubs” and on through the connected vehicle data marketplace.

So now maybe you’re thinking, “Dang, I never should have got rid of that Pinto.”But lucky for us, this anonymized vehicle tracking discovered golfers driving to golf courses and staying for two to six hours, indicating they’re likely playing a round of golf. This isn’t perfect – they could be hitting range balls or just hanging out at the bar. What the study is really counting is golf course visits, not rounds. And now for the big reveal.

The analysis compared two hours or longer of golf course trips between 2019 and 2022, and every day increased except Saturdays, which were already the week’s busiest. Trips more than doubled on Monday, Tuesday, and Wednesday nearly doubled on Thursday, and increased on Friday by a smaller amount, increasing total weekday trips by 33%.

Every hour of the day saw an increase in trips, typically leading with morning rounds, tapering off midday, but then jumping substantially at 3 PM and peaking at 4 PM, led by a 278% increase at 4 PM on Wednesday. In fact, most days, the number of trips at 4 PM equaled or exceeded those at 9 AM.

The explanation for the increase in weekday and afternoon play seems obvious – work-from-home gives employees flexibility in how they ration their time between work and leisure. They no longer commute, so time in the car, bus, or train can be transferred to the fairways. And, work hours can also be more flexible. Instead of the 9-5 grind so ingrained in our work culture, people have shifted to 7-3 or even 6-2.

The Stanford study notes that national productivity during and post-pandemic has been strong. It makes the case that golf courses receive higher usage by spreading play across the day and week, raising “golf productivity,” and increasing revenue. The reports by analysts like Pellucid and NGF bear this out.

The study also posits that WFH might be improving national productivity by “using personal assets – golf courses, shops, gyms, hairdressers, etc. more efficiently,” and intends in its next steps to examine other leisure activities easily identified from GPS coordinates, like malls, skiing, tennis, sporting events, etc.

Urban and suburban, and to a lesser extent, resort destinations, are the likely recipients of increased weekday traffic. And if your course is one of them, now you know why. If you are using one of the dynamic pricing technologies, it hopefully is tracking and adjusting rates accordingly. If you are not, it might be time to take another look at weekday, and especially weekday afternoon rates. You might be leaving money on the table. 

Harvey Silverman is a contributor to Golf Business and the proprietor of his marketing consultancy, Silverback Golf Marketing, and the co-founder of, golf’s only pay-by-hole app. Harvey authored NGCOA’s “Beware of Barter” guide and has spoken at their Golf Business Conferences and Golf Business TechCon.

🎙 Golf Business Podcast Episodes

** The views and opinions featured in Golf Business WEEKLY are those of the authors and do not necessarily reflect the position of the NGCOA.**