Racetrac's data science head on AI-driven operations at 700 convenience stores: from gut instinct to predictive analytics

Any relation to Brandon Jacobe with I don't think so. I think you guys differently. We have a we have a buddy who works uh he's a designer and we like to we like to poke fun of him because he is uh we call him Jacobe. Uh and and whenever we have a design problem, we always call him The last name sticks with that one.

Yeah. Anyway, um please introduce yourself for the stream. Who are you? What do you do? Happy to. Sorry, I'm out of breath. That's the last name. You're good. You're good. Um so, Matobi, I'm the uh head of data science and analytics at Racetrack. Okay. Um Southeast based fuel and convenience retailer. Yeah.

Um and shout out to my wife for letting me come up here because we're technically on vacation this week. I heard this. This is crazy. The grind never stops. We got the memo about lockin season. Well, it's you gentlemen. I couldn't pass up the chance. We really appreciate it. Okay. So, uh great to have you. Yeah.

So, so break down the business a little bit more. Give me a sense of the scale. Uh what the day-to-day is like, customers, you know, obviously we have a general idea, but give us more. Yeah. Yeah. Happy to share. So, um roughly 700 retail locations across our family of brands of uh Racetrack. Yep. Raceway. Yep.

And Golf. A lot of people don't realize that we we own Golf. Golf. Yep. Yep. Cool. um 10,000 employees um associates in our stores and people at our our um store support center in Atlanta. Um a lot of people don't know either.

We're top five largest privately held company in the state of Georgia and we are top 15 in the United States. Thank you. We have Minecraft.

Um, so walk me through a little bit of the history of the company because I imagine that what we're going to talk about in terms of like, you know, software artificial intelligence is, you know, a revision to the way it was done years ago, right? So, so yeah, walk me through a little bit of the history.

Get me up to speed. Oh, wow. Well, I can't speak to all of it. Um, I've been there about two years. Um, but what I can say is that we've done a really great job of focusing on transformation, specifically data enabled transformation.

Um actually I just wrapped up a conversation about this downstairs but um if you ask me one of the purest um use cases for transformation is converting from gutbased and tribal knowledge based decision-m to datadriven y and therefore after that analytics and AI based transformation.

So um you know we we've really focused heavily even before my time on making the best decisions we can with data. Y and so our partnership with Palunteer has really allowed us to to take that to the next level. Right. the proverbial next level.

Um, promised myself I would avoid buzzwords in this conversation, but it may not happen naturally. Um, but but but yeah, it's um it's been a a conscious and concerted effort um by our leadership top to bottom to to really make that happen. And it's not it's not easy at times, right?

You're you're asking people to step out of what they've done in the past and to trust data and math um that may or may not be right if we're just being candid. Yeah. Um, and so we've we've really grown and focused and and developed on on uh building that muscle with the organization top to bottom.

It's been a it's been a really really interesting and uh impactful two years with with our team this thus far. Walk me through some of the concrete ways that you can use data to make a decision at racetrack. I remember there's this funny story.

It might be might be apocryphal, but uh I heard that uh I always do this where I tell some story that might be entirely hallucinates. You're an LLM, but taking over. So So the story goes is that is that McDonald's needed to figure out how to place a bunch of restaurants.

I'm sure that this is something somewhat related to what you have to do.

you decide where the restaurants go and they did a ton of analysis and they figured out this street corner was the best and that street corner was the best and they spent millions of dollars in consulting and they put them all there and then Burger King came along and said, "Yeah, just put one next to to McDonald's.

" And uh there's some be there's some beauty there. There's some there's some hilarity there. Uh but uh but you can imagine that that's the type of very tractable problem. Where should I put a put a thing? Uh, also like store layout, planagrams, uh, figuring out what goes on promotion when, pricing, dynamic pricing.

Uh, there's a whole bunch of things that I could imagine you do, but like walk me through what you did or even at the individual at the individual store level where it's like, hey, we're out of this product. Yeah. What are the what are the problems? What's the most recent like case study you did? Yeah. Yeah.

Great question. Look at you talking about planagrams. Um, so so yeah, we we like to say that we're always focused on on the the customer, right? At the end of the day, it's our customers and it's our associates that make this massive business continue to run and thrive. Um, and so you're hitting on inventory.

That's that's a really important use case. Um, but even more important than that is making sure that we have the right levels of people at our stores to meet that customer demand.

There's nothing worse than when you go up to a gas station to fill up your your gas tank and there's a yellow bag on the handle or or I would actually argue it's it's even more painful when you you put it into your to and then it's slow or Yeah. or so there's there's that and there's also the inside experience, right?

We um we take pride in our um in our our food offering. So, totally fresh pizza um fresh sandwiches, breakfast sandwiches. Um and that takes people, that takes time, and that takes hours. and making sure that we we have the right level of people in the store, right number of hours and and the right skill sets as well.

It's not just an you can't just throw hours at these problems. Um you need to understand the skill set um to meet that demand and meet those expectations of the customer because at the end of the day um it really is that customer that that makes us continue to thrive. And you know, we got this pin on.

We're celebrating 95 years. Um we've been here a long time and we expect to be here a lot longer. 95 years ago, software didn't exist. it truly did not exist. And now you're sitting here implementing AI and and the largest enterprise software platform possible. Um uh switching gears, a little bit of a hot take.

Uh have you been surprised by the developments in just how the electric car has rolled out? Like there was a moment when everyone was like do not get in the gas station business at all. It's going to be all electric. All these companies are cooked.

Um, and then we saw the consumer kind of pull back from that and want a different experience and maybe they have a daily that's a, you know, Tesla and it's great, but then they also still are in the gas world in some ways. Um, have you has has has there been optimism inside the company for the future?

Well, we we are certainly investing in the future. Um, we Yeah, I was going to say people that are charging EVs, they want to they still want to get fresh pizza, right? They do. Exactly. Yeah.

the um and we we're actually taking a unique approach where we're we're developing that infrastructure and and those um those customer venues um on our own.

So we've chosen to to really understand the customer and do it in a way that that meets their expectations because um we can't predict what the future is going to going to hold 100%. Also a different experience right now because you might be stopping for 20 minutes instead of two minutes or five minutes.

That's a great point too. So you have a more captive audience for a longer period of time and um a lot of pride and all. Exactly. Throw something else. Come get Come get some racetrack swag in in the gas station. Yeah. Or anything of fresh pizza or what have you. But sit down for a minute.

We're certainly not turning a blind eye to what lays ahead. Um you know, we have certain strategies and things that we're talking about um to to make sure that we stay ahead. But it's a unique opportunity now to actually take that seriously.

you've seen where this market stabilizes and there's also just the standardization around NACS now like the actual charging port is standardizing so that probably makes the infrastructure cost a lot lot a lot less or a lot less risky I guess for you um yeah very very exciting um what so walk me through the actual like scale of the palunteer implementation are you early days are you trying to roll this out to all the employees you said 10,000 wasn't it something like that uh do you want everyone to interface with this or is this more of like a managerial tool that will be used to like make decisions about how to run the business.

Yeah, that's a great question. Um, I think right now we've really focused in on use cases that um are driven at the managerial level or or the head uh kind of the store support center level. Um, but that's certainly not to say that there aren't implications at our stores. Um, because there certainly are.

Um, and I think as we as we progress and as we deploy more and more use cases, um, I I very easily could see getting the technology in our frontline associates hands as as a real value ad and frankly a differentiator. Yeah.

Have you uh have you had any problems with uh different enterprise software companies not playing nicely together?

You don't have to name names, but uh we've just been tracking this story that there's now some AI companies that come out and say, "Hey, we want to take your, you know, your Google Docs and get it to talk to your Slack and Slack is owned by Salesforce, so they don't want to talk to each other.

" Uh and and and I'm wondering in the retail context if like a POSOS system and an inventory management system like there might be some similar sharp elbows or is it all pretty copacetic?

Yeah, I think it's uh fairly copathetic, but mostly because of of our IT team and the really great work that they've done from a data architecture standpoint and consolidating everything centrally and and really removing the need for kind of call it peer-to-peer communication of those of those platforms.

But because everything goes into data lake exactly and and you know again I I I think that that team really deserves a shout out too.

So while while our team is in the business um the IT and and the data team has really been an enabler for us uh we have a wealth of information and data that we can make some of these really complex decisions with.

Um and without it we would be severely hamstrung and would be working on challenges like pulling out of POS systems or what have you. And so we we've kind of we're past that level and we have a really strong data lake and infrastructure and architecture to to support all of the the nerdy math that my team loves to do.

Yeah. Awesome. Yeah.

What uh what what what else are you trying to uh identify going forward is I mean I imagine that like the base case is just like I want to know what stores are overperforming underperforming but then ideally you want to be able to predict which stores are going to start underperforming and intervene beforehand.

Is that roughly the Yeah, roughly. I think it depends on the use cases and and again not to throw buzzwords out there again but we break down analytics into four main types.

There is the descriptive so the old school reporting and dashboarding Tableau PowerBI u the diagnostic which explains the descriptive um and then my team really steps in uh on the predictive and the prescriptive front.

So, um, you know, think about, uh, predictive maintenance or, hey, this this fuel pump is predicted to go down in the next two or 3 weeks. That that predictive and prescriptive approach allows us to pivot again transformally away from being reactive um to being proactive with things that really impact our customer.

So, we like to really focus on, hey, where are the customer pain points? How can we um, peel that onion? how can we how can we solve some of those so they have a better experience and that that drives a lot of it too.

So so yeah it it um there's a world of use cases out there and we're really just scratching the surface. Very cool. One last question for me. Are there bad actors in the gas station business that intentionally pump the gas slow to drive people into the convenience store? Oh my gosh.

I would that flies in the face of everything that we think.

Well just because just the um so there there's we like to joke a lot about um you know on my team and maybe others share this sentiment or don't but um is it worse if a if a pump isn't working or or is it actually worse if a pump is slow and I actually think my experience are the most painful um when I go up to a pump and it just it's slowly ticking at least when when you see a bag you see the yellow handle just don't even don't go there yeah don't go there and I don't think I just remember maybe maybe it was cuz when I was a kid and I was broke and I'd put like $20 on pump five and it just felt like it'd go fast.

And now as a as an adult I'm I can I just get but but I'm getting like five times the amount of gas, right? I'm just like you weren't going to race tracks cuz we predict when that's down for racrack do anything slowly. Speed is in the name of this company for 93 years. 95 years 95 years. I can't wait for 100.

You'll have to come back on. That would last you a hundred years of racetrack data analysis. Break it down. We'll do a 100 hour stream year by year. I mean, it must be fascinating. Name every data point. I mean, just pulling like the revenue over a 93 year ramp. Like, that's got to be fascinating. That' be interesting.

Fascinating. Anyway, thank you. Thank you so much for coming on and interrupting your vacation. This is great. We'll talk. Enjoy the conference. Have a great rest of your day. Enjoy the conference. And that's uh our last guest for the day. Right. our last guest for the day. Started out with a bang.

We should run out we should run uh well run through a thank you to all the sponsors that make this possible. We told you about ramp. com. Time is money. Save both. Uh we are of course powered by Reream one live stream 30 plus destinations. Uh of course we won't need to tell you about Figma. Think bigger, build faster.

Go to figma. com for all your design needs and get compliant on vanta. com. Manage risk, prove trust continuously. We also got graphite. dev supporting us. Code review for the age of AI. Poly market of course. Uh some big news out of Poly Market. There was a major trade deal. We'll talk about that tomorrow. Okay. Okay.

Um uh Julius, what analysis do you want to run? You can chat with your data and get expert level insights in seconds. Turbo Puffer, our newest sponsor. Search every bite. Serverless vector and full text search. Build for first principles on object storage.

Uh, profound if you want to get your brand mentioned in chat too, go to profound. Linear, of course, is a purpose-built tool for planning and building products. Big day for linear. Big day for big uh if if uh getting lots of shout outs at the Atlassian.

If Atlassian is paying 620, 610 for the browser company, they should get ready to pay 6 trillion for linear. I think so. Uh we are we have we are of course supported by numeral numeralhq. com sales tax on autopilot. Uh Finn. AI the number one AI agent for customer service.

Adio customer relation customer relationship magic. Adios is the AI native CRM that builds scales and grows your company to the next level. Uh we of course sleep on eight sleeps. You can go to eight. com. Uh we are also supported by public. com investing for those that take it seriously.

Uh, and we always tell you about adquick. com advertising made easy and measurable. Adquever. And if you noticed, Dr. Karp was wearing a fantastic PC Philippe Aquinaut orange strap. Uh, and if you want one for yourself, you can go to bezel get bezel. com.

Your bezel concierge is available now to source you any watch on the planet. Seriously, any watch. I'm sure that they would love to find you uh a orange band aquat. Uh Business Insider has a scoop here that says Palanteer CEO Alex Karp says top tech talent is about to get crazy valuable.

Alex Karp, CEO of Palunteer set on quote unquote TV. Why do they put us in quotes? This is the dividing line. They put us in quotes. This is the dividing line. Close the laptop. Okay, so business insider. Oh wow. The website Business Insider, wow, says that top tech.

I think I think we got to I think we just got to put like the just one of the words in quotes. It can't be quote business insider. Be a business insider. That is the way we talk. I got to look in I actually have to look into this company because um I love business and I love I love insider trade.

Insider insiders in business. Isn't that the lore? Isn't that the lore? Henry Bogget, the guy who started business insider loved insider. I thinking I think he lost his I think he lost his license. I'm not kidding. I'm not kidding. Okay, look this up. Business insider insider history. And more breaking news.

Justin Bieber is uh launching Swag 2 tonight. The new album. What does that mean? and Meek Meek Mill posted two hours ago. Meek Mill becomes a AI founder.

So according to Wikipedia, according to Wikipedia, uh Henry Blogget was charged with civil securities fraud by the US SEC settled the charges uh with payment of 4 million. Uh he was permanently borrowed from the securities industry by the SEC and the NYC.

The charges uh arose during the dotcom boom at Meil Lynch um where which included issuing materially misleading re research reports on internet companies and making exaggerated or or unwarranted claims about them to customers and uh and then in 2007 four years later he co-founded Business Insider which is a fantastic punt.

Like it's it's so funny. It's so funny.

He's the he's he was in the business of insider trading and he said why did I com combine they didn't say insider trading they said civil securities fraud it doesn't sound great but uh you know after your run Jeff Bezos purchased a stake in Business Insider and he he had a great run 2007 to 2023.

Uh anyway, there's so many great quotes from the the carb segment. This one I would say, he says, I would say modestly, I'm the most humble I've ever been. You would never build a software company downstream from value creation.

It's all how do I make the client feel like they're getting laid while they're getting effed. So good. Uh the founder Adam who introduced AI key, a small device that lets AI control your entire phone. Just plug it in and ask it to complete a task. He's saying all of this all of this and still no TVPN invite.

Uh we should we should probably have him on. A lot of people a lot of people were uh said no thanks because uh I guess he previously worked in military intelligence and and uh people didn't feel inclined to plug a hardware device into their into their phone.

But but we're we're in the capital of military intelligence right now. It looks like uh he sold out uh the the initial batch. So let's have him on uh put the timeline in turmoil. Anyone who puts the timeline in turmoil is welcome on the show. I'll give him a follow right now and we will make it happen.

We're we're a lot of people are having fun with the stream. This is a great reaction. Uh anyway, uh that's our show. We got to get out of the United States and back to the United States. We do. Uh, last thing, this just because it is breaking and it's funny.

OpenAI plans to launch an AI powered hiring platform by mid 2026, putting the outfit in close competition with LinkedIn with with LinkedIn. The company also wants to start certifying people for AI fluency. Uh, that you are you AI fluent? This seems bad.

Yeah, this seems like more of a Meror competitor than LinkedIn maybe. I don't know like um I yeah, we we need to dig in more to that. But the but the other odd thing is that wouldn't Microsoft get a copy of whatever they build. So wouldn't wouldn't Microsoft get access like if they build a new I mean that's the deal.

That's the nature of the deal is that they get they get the rights to AI OpenAI's IP. So if they build something that's valuable but if they build a network then that's a separate thing, right?

because the the the IP doesn't matter as much like like the the weights to GBD5 are not as valuable as asatform as the chat GBT app. So yeah, maybe may maybe there's something there. I don't know. People have been complaining about LinkedIn for a long time. So maybe maybe there's What is this?

Donald Boat says that he has art for the Ultra Dome. Oh yeah. Yeah. I was I was talking to him about that. I'm very excited. Great. He made something. So Well, I wish we could keep streaming, but we got to get back to uh we got to go. Okay, let's go. All right, folks. Anyway, thank you today. We love you.

Back to a regular show tomorrow. Have a great afternoon. Bye.