Artwork for podcast Supply Chain LEAD Podcast
Computer Vision in Retail with 1retailAI (Part 1)
Episode 3614th June 2023 • Supply Chain LEAD Podcast • Supply Chain LEAD Podcast
00:00:00 00:32:21

Share Episode

Shownotes

Mike Graen dicusses Computer Vision with Pierre Marie Rallu - CEO of 1retail AI - about how CV and AI can help companies know what they have and where it is located, as well as specific use-cases and best-practices.  

Transcripts

Mike Graen:

Hello, my name is Mike Graen. Welcome to the

Mike Graen:

Supply Chain Management Research Council focused on on shelf

Mike Graen:

availability. I'm your host today and I'm joined today by

Mike Graen:

Pierre Marie Rallu, who's the CEO of 1retailAI. They are a

Mike Graen:

company that works very closely with SES-imagotag to understand

Mike Graen:

on shelf availability using computer images. Please join me

Mike Graen:

for with my conversation with Pierre. Thank you very much and

Mike Graen:

good afternoon. We are absolutely thrilled to have

Mike Graen:

Pierre here with us. We're going to spend a little bit of time

Mike Graen:

talking about our favorite topic, which is on shelf

Mike Graen:

availability, not a big surprise and sense this is kind of the

Mike Graen:

focus that we've had for quite a while in this space. But before

Mike Graen:

we get into the specifics of appeared, we'd love to have you

Mike Graen:

kind of unmute, introduce yourself to our audience, and

Mike Graen:

give us a little bit of background on yourself.

Pierre Marie Rallu:

Thank you, Mike. Thank you for having me

Pierre Marie Rallu:

today on the podcast. So my name is Pierre Marie Rallu, as you

Pierre Marie Rallu:

just stated. I've been in the retail technology for retail

Pierre Marie Rallu:

world for about 20 years, more or less in the forecasting,

Pierre Marie Rallu:

replenishment and supply chain space; in-store, warehouses and

Pierre Marie Rallu:

all of the above. I started 1retailAI a couple of years back

Pierre Marie Rallu:

to help startups especially focus on AI technology to grow

Pierre Marie Rallu:

in the retail segment, the retail vertical in the US. That

Pierre Marie Rallu:

has been has been most of my career has been studying or

Pierre Marie Rallu:

helping companies grow in that segment. So that has been a core

Pierre Marie Rallu:

a core theme.

Pierre Marie Rallu:

That's outstanding. Well, you and I have something in common.

Pierre Marie Rallu:

I've been doing it 40 years, you've been doing it for 20

Pierre Marie Rallu:

years. I guess the good news and the bad news is we're still

Pierre Marie Rallu:

employed because there's still an opportunity right? Haven't

Pierre Marie Rallu:

quite got figured out. Ever since the first retail store got

Pierre Marie Rallu:

opened, we've always got issues with on shelf availability. And

Pierre Marie Rallu:

if you are one of the things that I always ask my my my

Pierre Marie Rallu:

guests on this on this podcast or this conversations on retail

is the following question:

take your day job away for a second

is the following question:

put that on the side, put yourself in the shoes of a

is the following question:

customer because the all that we can we can we can think about

is the following question:

from a technology standpoint, from an AI standpoint, at the

is the following question:

end of the day, our best experience is going to be being

is the following question:

a customer shopping in a store. So any stories that you could

is the following question:

provide to us where you actually as a customer went in to

is the following question:

purchase a product, and we're disappointed that it wasn't

is the following question:

there you don't have to call off the retail or the brand or

is the following question:

anything like that. But tell us how you felt through that, what

is the following question:

did you do about it, etc, it would be pretty interesting to

is the following question:

hear.

is the following question:

I think that's the key one, there are actually two stories

is the following question:

you want to mention here you want to talk about showing up in

is the following question:

the store with a specific need and not finding what you want or

is the following question:

going online buying something and not getting what you want.

Mike Graen:

Both of them are painful.

Pierre Marie Rallu:

I have I have three daughters here we're

Pierre Marie Rallu:

all very specific, where they want to eat and drink and things

Pierre Marie Rallu:

like that. And we shop a lot online I mean my wife and I both

Pierre Marie Rallu:

work so we tend to you know use Instacart or ship though or

Pierre Marie Rallu:

directly the retailer websites and again no names but I would

Pierre Marie Rallu:

say almost 100% of the time one or two products are being either

Pierre Marie Rallu:

substituted or just removed from the delivery and a best case

Pierre Marie Rallu:

scenario is substituted by something which is kind of

Pierre Marie Rallu:

similar which is fine or worst case scenario that just moved

Pierre Marie Rallu:

the Nutella to another brand and that's a disaster the house

Pierre Marie Rallu:

every single exploding out there. So so so I think

Pierre Marie Rallu:

everybody has as this as this as experienced already. And when

Pierre Marie Rallu:

you show up at the store it's that was a couple of things

Pierre Marie Rallu:

which are which are main pain painful main pain tickets for

Pierre Marie Rallu:

the for the clients is really like Well, first of all, not

Pierre Marie Rallu:

finding your products, and can be the product itself. It can be

Pierre Marie Rallu:

the brand you want, it can be audited the fact to go and

Pierre Marie Rallu:

search for the product and having to spend 1015 minutes to

Pierre Marie Rallu:

look for the exact product you need in the grocery store can be

Pierre Marie Rallu:

pretty large. So those are some of the experiences that you see

Pierre Marie Rallu:

that that are that are that are an issue currently in the

Pierre Marie Rallu:

customer journey.

Mike Graen:

Yeah, hey, I guess two other things is you know,

Mike Graen:

typically if you're looking and you think you already checked

Mike Graen:

the website and they said they have four of them and you go to

Mike Graen:

the shelf and they're not there. The obvious thing is to ask a

Mike Graen:

employee of the of that company Hey, do you have any of these?

Mike Graen:

Well, it says we have four and those dreaded words let me go

Mike Graen:

back in the back and look for them which basically means

Mike Graen:

you'll be standing there for a while before that person

Mike Graen:

probably are actually returns. The other one which is

Mike Graen:

interesting is either my kids or my wife will look at me go is Is

Mike Graen:

this what you do? Isn't this supposed to be fixed? Because

Mike Graen:

you guys work on this stuff? So somehow you get it? Yeah, not

Mike Graen:

only did I disappointed because it's not there. But you know,

Mike Graen:

somebody throws me under the bus because that's my job to fix

Mike Graen:

that. So well, that's awesome. Well, the point is, we all are

Mike Graen:

customers as well. So we've all experienced either ordering

Mike Graen:

something online, going to pick it up and store it and not being

Mike Graen:

there or going through and getting major substitutions or

Mike Graen:

eliminations of things that you really need in the store. And so

Mike Graen:

part of what we want to spend some time talking about is tech.

Mike Graen:

Now certainly there's a people and a process portion of that in

Mike Graen:

a supply chain, it says there's lots of reasons why things

Mike Graen:

aren't on the shelf. But one of the things that we do is try and

Mike Graen:

work against technology to at least least lets people know

Mike Graen:

about that. So tell me about your company. I know you're

Mike Graen:

integrated are working very closely with SES-imagotag,

Mike Graen:

you're part of them now. Tell me exactly what you do with with

Pierre Marie Rallu:

Sure, yeah. So I started 1retailAI a couple

Pierre Marie Rallu:

of years ago, in order to work with many startups, as many

Pierre Marie Rallu:

with the company you have now.

Pierre Marie Rallu:

startups as I can in the retail world, and help them grow in

Pierre Marie Rallu:

that region. And as you mentioned, you're absolutely

Pierre Marie Rallu:

right. I mean, there is technology, there is process and

Pierre Marie Rallu:

there is people and actually it start with people and then

Pierre Marie Rallu:

process and then technology. And quite a firm and the technology

Pierre Marie Rallu:

can be really good. But if the technology doesn't fit into the

Pierre Marie Rallu:

process, and if the people don't use that technology, well, this

Pierre Marie Rallu:

technology is very useless. And therefore, part of what I'm

Pierre Marie Rallu:

doing is looking at, okay, what does the return what needs what

Pierre Marie Rallu:

makes sense to me? And where do I see value. And then I start

Pierre Marie Rallu:

working with those companies. For example, I started to work a

Pierre Marie Rallu:

year and a half ago with with a startup called be live.ai. And

Pierre Marie Rallu:

they are specialized in computer vision, AI, and the And so

Pierre Marie Rallu:

basically, what they do is you put cameras on the shelf, and

Pierre Marie Rallu:

the cameras is watching the opposite shelf, and then taking

Pierre Marie Rallu:

pictures all the time in near real time. And then there are

Pierre Marie Rallu:

big AI algorithms behind the scenes that are analyzing the

Pierre Marie Rallu:

products, looking at doing deep learning, understanding the

Pierre Marie Rallu:

products exactly as you and I recognize a product on the

Pierre Marie Rallu:

shelf, the AI does the same thing. And then they look at

Pierre Marie Rallu:

okay, what is out what is partially out what is out of

Pierre Marie Rallu:

place, or upside down all these kind of things, and then help

Pierre Marie Rallu:

the employees to guide them through the store. The real time

Pierre Marie Rallu:

basis had prioritized and step six. So I really liked the idea.

Pierre Marie Rallu:

And we will come back we both lost the pension. But we'll get

Pierre Marie Rallu:

back to it. But I really liked the idea. And it happened that

Pierre Marie Rallu:

we live has been acquired very suddenly by SES-imagotag. And to

Pierre Marie Rallu:

join the the business unit of computer vision of ACS. So so

Pierre Marie Rallu:

now I'm very close to SES. Understanding how we are merging

Pierre Marie Rallu:

the solutions, and how we were building the building that

Pierre Marie Rallu:

vertical especially in North America. That's only a bit

Pierre Marie Rallu:

though. And I just, I just spent the week actually, I just spent

Pierre Marie Rallu:

a week actually with with with the SES leadership team in the

Pierre Marie Rallu:

retreat in France, not too shabby. The chateau.

Mike Graen:

It only took you 10 minutes to tell me you just got

Mike Graen:

back from Paris. That's just not right.

Pierre Marie Rallu:

We will, we will skip the champagne referenc

Pierre Marie Rallu:

.... But, the company has a vision, which is very

Pierre Marie Rallu:

interesting. And and I think it fits pretty well where the

Pierre Marie Rallu:

retail retail world is right now.

Mike Graen:

Yeah, just and just for our audience. SES-imagotag

Mike Graen:

is an incredible company, I've worked with him quite a bit

Mike Graen:

actually worked with him when I was at Walmart with electronic

Mike Graen:

shelf labels, etc. Bringing bringing basically digital

Mike Graen:

intelligence to the shelf, right whether at shelf labels, whether

Mike Graen:

it's cameras, in your case, taking that camera methodology

Mike Graen:

and being a look at the opposite side of the of the aisle and say

Mike Graen:

it because it's really important. Everybody say well,

Mike Graen:

we should be able to look at a shelf and say there's a label

Mike Graen:

and there's no product. That's pretty easy. But there's also

Mike Graen:

there's a label and there's product, but it's the wrong

Mike Graen:

product. We call those incorrect products or plugs. We see times

Mike Graen:

where the price at the register and the price actually at the

Mike Graen:

shelf in the paper label world environment are different.

Mike Graen:

That's a problem. So talk to us a little bit about your method,

Mike Graen:

that methodology of literally using computer vision. I'm

Mike Graen:

saying I'm assuming it's real time computer vision to to

Mike Graen:

identify what the opportunities are on the shelf.

Pierre Marie Rallu:

Yeah, absolutely. Let me let me give a

Pierre Marie Rallu:

step back, which is one thing which is very important to

Pierre Marie Rallu:

understand as well as maybe understand some of the forces of

Pierre Marie Rallu:

the market and why that makes sense now. I mean, you mentioned

Pierre Marie Rallu:

this is a good it's a good thing which is actually 30 years old,

Pierre Marie Rallu:

which is in the technology word like a dinosaur. But in the

Pierre Marie Rallu:

meantime, it really, really behave as a startup or multiple

Pierre Marie Rallu:

startup, I would say. And, and so the company, as you

Pierre Marie Rallu:

mentioned, as being has been, has been known the number one in

Pierre Marie Rallu:

the world for ESL, so the electronic shelf labels, which

Pierre Marie Rallu:

is their historical job. But they have recently transformed

Pierre Marie Rallu:

under CEO Thierry, Thierry Gadou and to become a real offer

Pierre Marie Rallu:

around digitization of the physical store. And what we see

Pierre Marie Rallu:

right now is, I mean, ESL has been in Europe, on the shelf of

Pierre Marie Rallu:

every grocery store for 20 years. I mean, I grew up with

Pierre Marie Rallu:

ESL, and not 20 years old. And the the, and surprisingly,

Pierre Marie Rallu:

arrive in the US in early 2000s. And I didn't see a single ESL

Pierre Marie Rallu:

anywhere. And as of today, I mean, it's very, very rare to

Pierre Marie Rallu:

find the essays on the shelf, when we're talking about we're

Pierre Marie Rallu:

talking about two or 3% market penetration, which is compared

Pierre Marie Rallu:

to 6065. And in Europe, and what we see is that the market has

Pierre Marie Rallu:

evolved itself, the US market has evolved, I mean, under the

Pierre Marie Rallu:

under the global pressure, the rising labor costs, the energy

Pierre Marie Rallu:

costs going up the and then the e-commerce, the pressure of

Pierre Marie Rallu:

e-commerce, to align the experience, customer experience

Pierre Marie Rallu:

in the store. All of that is bringing a lot of pressure on

Pierre Marie Rallu:

transforming the brick and mortar experience. And a lot of

Pierre Marie Rallu:

that is, and this is why the office is makes a lot of sense.

Pierre Marie Rallu:

Because the fact of digitizing the store - basically realign a

Pierre Marie Rallu:

little bit - the econ and the brick and mortar stores, stores.

Mike Graen:

Got it. That's great. That's great macro.

Pierre Marie Rallu:

And they are and they are and then after of

Pierre Marie Rallu:

course, we got to talk about the ESL, which is blooming in the

Pierre Marie Rallu:

US. And so being being in that market right now makes a lot of

Pierre Marie Rallu:

sense. But then above and beyond just ESL, which are driving

Pierre Marie Rallu:

dynamic pricing and promotion policies and things like that

Pierre Marie Rallu:

much faster and much easier. There are a number of

Pierre Marie Rallu:

technology, including computer vision and AI that are also

Pierre Marie Rallu:

going to help you digitally that story. Yeah, digitalizing that

Pierre Marie Rallu:

store.

Mike Graen:

I know that I know, the electronic shelf labels, I

Mike Graen:

know that's not your specific area of focus. But not only does

Mike Graen:

it provide you consistent pricing and correct pricing at

Mike Graen:

the shelf, so that shelf price and the price at the register

Mike Graen:

are the same price versus a different price. But also you're

Mike Graen:

building intelligence into those now we're literally, if I'm

Mike Graen:

picking items for a customer, as I turn around the corner, and I

Mike Graen:

have two of these that I'm looking for, they have LED

Mike Graen:

lights that can blink, blink to me and say, Hey, I'm right here,

Mike Graen:

pick right here. Rather than, where's that item, there's a

Mike Graen:

whole bunch of items. I mean, when you're talking about great

Mike Graen:

big, you know, things that paper towel, it's not that hard when

Mike Graen:

you're thinking about cosmetics or things that are very SKU

Mike Graen:

intensive, that that that will be called picking operation

Mike Graen:

becomes easier. And from a stocking standpoint, allowing an

Mike Graen:

associate or a employee to pick out an item, scan the UPC and

Mike Graen:

have it blink to where it goes, rather than trying to find in a

Mike Graen:

big four foot section where it's supposed to go, I think is a

Mike Graen:

game changer. Let's focus back on the auto stock work because

Mike Graen:

that's the most exciting part of this. So it's exciting time to

Mike Graen:

be part of retail. So where is AI and computer vision today?

Mike Graen:

And where do you see it kind of going in the future? So starting

Mike Graen:

with kind of the US market? Because I think you're right is

Mike Graen:

it's a little bit behind where Europe is? Where is it today?

Mike Graen:

And where do you think it could go in the future.

Pierre Marie Rallu:

So, curiosity what we see, so if you

Pierre Marie Rallu:

think about the supply chain in the in the retail and most

Pierre Marie Rallu:

supply chains, the purpose of the supply chain is to bring the

Pierre Marie Rallu:

right product at the right place at the right price, right. So in

Pierre Marie Rallu:

the written world, that will mean that when you want to have

Pierre Marie Rallu:

the product on the shelf, when the when the consumer and the

Pierre Marie Rallu:

customer is coming in look for it. Well interested in almost no

Pierre Marie Rallu:

retailers can actually know that the product is on the shelf at

Pierre Marie Rallu:

the time they know it. They might know best case scenario

Pierre Marie Rallu:

they might know they have it in the store. But they don't know

Pierre Marie Rallu:

if it's on the shelf when the customers looking for it. And

Pierre Marie Rallu:

you think about all the for the messy recesses the debate

Pierre Marie Rallu:

expands in terms of supply chain logistics to the store the

Pierre Marie Rallu:

store, or the or the or the automation of the replenishment

Pierre Marie Rallu:

or the planet prime automation and so on. And still I mean, we

Pierre Marie Rallu:

can't say if the product is there, so I think this is what

Pierre Marie Rallu:

This is that vision that we're bringing with that technology,

Pierre Marie Rallu:

when I say vision based, but this computer vision that we're

Pierre Marie Rallu:

bringing, the idea is to have an AI on the shelf, that looking at

Pierre Marie Rallu:

those products permanently, real time or near real time. And that

Pierre Marie Rallu:

either to address the information that the product is

Pierre Marie Rallu:

out is low or, or short. And then being able to drive the

Pierre Marie Rallu:

store operations and the supply chain in order to improve that

Pierre Marie Rallu:

stock position. So they are coming back just a little

Pierre Marie Rallu:

background. And going back to what you said. I mean, I would

Pierre Marie Rallu:

say Europe and the US are about the same level on this one esse

Pierre Marie Rallu:

a different ballgame for sure. But Computer Vision we're

Pierre Marie Rallu:

talking about and emerging technology. And we will come

Pierre Marie Rallu:

back to it. And so I would say the players in Europe and

Pierre Marie Rallu:

players in the US are tip-toeing at the moment on where we are.

Mike Graen:

Yeah, so just got a text message from somebody. So

Mike Graen:

I'm going to ask you a question that's kind of off script here a

Mike Graen:

little bit. As you think about a big mass merchandiser like a

Mike Graen:

Walmart or a Target or somebody, you got some product on certain

Mike Graen:

parts of the store that computer vision makes all the same. You

Mike Graen:

have other product categories, like apparel, and maybe

Mike Graen:

electronics, etc. That may make may be different, right? So how

Mike Graen:

does computer vision? How does confuse you? Because I don't

Mike Graen:

think computer vision is a one stop solution for everybody. I

Mike Graen:

don't think RFID is one stop solution for everybody. How do

Mike Graen:

you see these technologies working together for different

Mike Graen:

kinds of categories, like apparel versus boxes of cereal?

Pierre Marie Rallu:

That's a very good point. So computer

Pierre Marie Rallu:

vision is good for what you can see easy. I mean, when you have

Pierre Marie Rallu:

the you have a box of cereal on the shelf on now they have. So

Pierre Marie Rallu:

and they will divide that. And then there are areas as you

Pierre Marie Rallu:

mentioned, it's very difficult to recognize a black T shirt

Pierre Marie Rallu:

size L from a black T shirt size average just by vision. So that

Pierre Marie Rallu:

is a little bit of it's a little bit of the limits to certain

Pierre Marie Rallu:

degree. But just just computer vision itself has been evolving

Pierre Marie Rallu:

pretty fast. Meaning that, for example, I mean, over the last

Pierre Marie Rallu:

six months, I spent a lot of time on produce. And the

Pierre Marie Rallu:

capability to actually recognize the produce, making a difference

Pierre Marie Rallu:

between the banana and orange and Apple understanding the

Pierre Marie Rallu:

level of the lottery ever produce on the shelf. With this

Pierre Marie Rallu:

limitation, of course, I mean, but we will, and understanding

Pierre Marie Rallu:

your so the directness of the product is a product, I mean

Pierre Marie Rallu:

mature, not mature, how long time has been standing on the

Pierre Marie Rallu:

shelf. So looking because the cameras are looking at the

Pierre Marie Rallu:

product, I mean, we can see if a product that has used by a shelf

Pierre Marie Rallu:

life of a couple of hours has been sitting on the shelf for a

Pierre Marie Rallu:

couple of hours. And then there are a lot of business cases that

Pierre Marie Rallu:

are being being that are being developed above and beyond the

Pierre Marie Rallu:

standard grocery grocery or GM merchandise, or GM categories.

Pierre Marie Rallu:

So there are there are a number of number of categories that are

Pierre Marie Rallu:

that are good, very good candidates for for computer

Pierre Marie Rallu:

vision. And then you mentioned I think those are technologies

Pierre Marie Rallu:

around the store and, and the store digitization and that's

Pierre Marie Rallu:

when it'll be the idea of ACS is not a one stop shop of one

Pierre Marie Rallu:

technology, you're going to have a number of technology that are

Pierre Marie Rallu:

going to be complementary. For example, you can have smart,

Pierre Marie Rallu:

smart brochures that are counting products on the shelf,

Pierre Marie Rallu:

you can have scales that are weighing the product on the

Pierre Marie Rallu:

shelf. And then when you start having this mix of committed

Pierre Marie Rallu:

this mix of technologies, we start having a very much more

Pierre Marie Rallu:

accurate visibility of what you have on your in your store.

Mike Graen:

Okay, well so you just opened up a very

Mike Graen:

interesting conversation because typically people say, Well

Mike Graen:

computer vision is great it tells you if the products on the

Mike Graen:

store. But unlike things like RFID computer vision can't count

Mike Graen:

I can see the first one but I can't see the ones behind it.

Mike Graen:

You just uncovered something those pushers the weight sensors

Mike Graen:

talk to us a little bit about the role that they play in not

Mike Graen:

only the product is available, but how many are on the shelf

Mike Graen:

and it also could generate a signal to a store associate

Mike Graen:

saying hey, by the way, a new case can now fit it couldn't fit

Mike Graen:

a few minutes ago but it can now fit walk us through that.

Pierre Marie Rallu:

What this example of the case shows that

Pierre Marie Rallu:

you know retail pretty well. I mean understanding that you have

Pierre Marie Rallu:

one or two cans of soup is the one thing. Understanding you

Pierre Marie Rallu:

have room for a new case of soup is another thing, right? Because

Pierre Marie Rallu:

when we're thinking demo replenishment, I mean we don't

Pierre Marie Rallu:

buy it by the SKU right we buy by the by the PCB we buy by the

Pierre Marie Rallu:

case or the pack. And so and so they they are the this is the

Pierre Marie Rallu:

this is the this is the this is where this is where the

Pierre Marie Rallu:

replenishment is understanding replenishment is very important.

Pierre Marie Rallu:

It's not just a number of understanding the exact

Pierre Marie Rallu:

quantity, which chef rather that, is it the time to order a

Pierre Marie Rallu:

new pack on that. And so, when you think about just computer

Pierre Marie Rallu:

vision, what can the computer vision do work, computer vision

Pierre Marie Rallu:

is going to look at the horse on the shelf, you're going to look

Pierre Marie Rallu:

at, if a product is, is low on that, we can see that if there's

Pierre Marie Rallu:

one facing of two facing or three facings. And the computer

Pierre Marie Rallu:

vision will be able to, to understand if a product is not

Pierre Marie Rallu:

at the right place or not. Okay, if your your planograms, you're

Pierre Marie Rallu:

supposed to have to face things, and suddenly you're three or

Pierre Marie Rallu:

four because you're missing a product on the side. I mean,

Pierre Marie Rallu:

that makes sense. And so those are some of the business cases

Pierre Marie Rallu:

that computer vision can solve. And then it's going to guide the

Pierre Marie Rallu:

employees toward what actually matters. Because at the moment,

Pierre Marie Rallu:

if you get a standard grocery store, why would you go you're

Pierre Marie Rallu:

gonna go and scan your gaps and check if I had my zero. Do I

Pierre Marie Rallu:

have quantity on hand, is it going to be delivered today? But

Pierre Marie Rallu:

you have to go check your your, your your scanning your gaps on

Pierre Marie Rallu:

a regular basis. The problem of doing that is even if you manage

Pierre Marie Rallu:

preparatory inventory, when you look at the shelf, you don't

Pierre Marie Rallu:

know if there is definitely inventory until you check it.

Pierre Marie Rallu:

Well, that's what computer vision will do for them, we're

Pierre Marie Rallu:

gonna go to receive the file of your balance on hand, and

Pierre Marie Rallu:

compare that with what you have on shelf and just manage the

Pierre Marie Rallu:

exception. So definitely don't certainly don't have to scan the

Pierre Marie Rallu:

2, 3, 4 thousand holes you have on the shelf, but just maybe the

Pierre Marie Rallu:

five or 600 that are actually never in the store. And when

Pierre Marie Rallu:

they say actually, maybe they're on the back room, maybe they're

Pierre Marie Rallu:

on the riser, if you have an inverter on the riser, or maybe

Pierre Marie Rallu:

the the quantity is wrong. And then you need to adjust the

Pierre Marie Rallu:

quantity. And when you do that on the daily basis, what you'll

Pierre Marie Rallu:

start to you start to to have a much leaner replenishment when

Pierre Marie Rallu:

every day you correct your balance on it. And we can talk

Pierre Marie Rallu:

about why the middle southern discrepancies. But when every

Pierre Marie Rallu:

day you are cleaning your your stock in the store, but your

Pierre Marie Rallu:

punishment gets better. Your punishment gets better gets

Pierre Marie Rallu:

leaner, your your other stock goes down, but your inventory

Pierre Marie Rallu:

level goes down as well, because you'll have excess inventory.

Pierre Marie Rallu:

And all of that drives a much leaner supply chain because your

Pierre Marie Rallu:

your demand, which is the store much more accurate. Okay,

Pierre Marie Rallu:

perfect. Second part of your question, just finishing you

Pierre Marie Rallu:

asking you about the pushers. What the pushers are going to

Pierre Marie Rallu:

RFID ideas? Well, everything which is attached to the unit

Pierre Marie Rallu:

will be able to actually count the product. And counting the

Pierre Marie Rallu:

product is a very important, it's very important information,

Pierre Marie Rallu:

especially in specific categories. When if you're going

Pierre Marie Rallu:

cosmetics with very high margin high price products, when a case

Pierre Marie Rallu:

is expensive. So you want to make sure that you're ordering

Pierre Marie Rallu:

at the right point. So knowing the number of products you have

Pierre Marie Rallu:

in this category, pharmacy, cosmetics, and then we can go in

Pierre Marie Rallu:

after hours. Well, I mean, we have different way of counting

Pierre Marie Rallu:

the counting the product on the on the on the hanger. And so and

Pierre Marie Rallu:

so those technologies provide a much more granular visibility on

Pierre Marie Rallu:

the accounts. And that enables more precision in your replenishment.

Pierre Marie Rallu:

Got it. So JW has asked basically a really good

Pierre Marie Rallu:

question. I think from from my perspective, he was interested

Pierre Marie Rallu:

in, hey, give me a one give me a one or two or three use cases

Pierre Marie Rallu:

for computer vision AI, versus kind of what the typical rain

Pierre Marie Rallu:

RFID which is basically UHF RFID that a retailer might choose.

Pierre Marie Rallu:

What are those use cases from a computer vision that you think

Pierre Marie Rallu:

stand out as a differentiator?

Pierre Marie Rallu:

Well, first of all, as far as I know, I know only one chain that

Pierre Marie Rallu:

has enabled RFID across all its product in its entire chain. And

Pierre Marie Rallu:

that's Decathlon, a sporting goods chain, and their

Pierre Marie Rallu:

experience is fantastic. And when you pick whatever you want

Pierre Marie Rallu:

in the in the store, everything 100% of the products are RFID.

Pierre Marie Rallu:

And then you go through through the gate, and then it flashes,

Pierre Marie Rallu:

the RFID and then the building. So you still have to go and

Pierre Marie Rallu:

bidding in the case but no counting no need to burden. I

Pierre Marie Rallu:

mean, this is a fantastic experience. But they it was

Pierre Marie Rallu:

never for it. They were able to deliver it for a couple of

Pierre Marie Rallu:

reasons. First of all, sporting goods company. So I mean, we're

Pierre Marie Rallu:

not talking about you're talking about fairly high price. We have

Pierre Marie Rallu:

a [?] and they're almost - I don't know the exact number but

Pierre Marie Rallu:

they have a very high level of privacy but they manufacture

Pierre Marie Rallu:

probably 50% more of their goods. So since they manufacture

Pierre Marie Rallu:

both embed the RFID from the manufacturing process, and then

Pierre Marie Rallu:

spend a lot of time for those are 50% to RFID themselves in

Pierre Marie Rallu:

the warehouse. So that's an investment that seems to be

Pierre Marie Rallu:

paying at the store level. So RFID is great. But if you take a

Pierre Marie Rallu:

Walmart's that have, I don't know, 120,000 SKUs, a lot of

Pierre Marie Rallu:

them are very low cost. And enabling the RFID is very

Pierre Marie Rallu:

complicated, it's actually not done at all. And therefore,

Pierre Marie Rallu:

therefore, what we look at computer vision, because it's

Pierre Marie Rallu:

much easier to enable it's much more realistic in the store at

Pierre Marie Rallu:

the moment, and provide a mass solution. So ideally, every

Pierre Marie Rallu:

single day RFID, and then life is great, well, reality of the

Pierre Marie Rallu:

supply chain is different. So, of course, I need the business

Pierre Marie Rallu:

case, what was really what I'm trying earlier, is really like

Pierre Marie Rallu:

being able to be super specific on how to get organized in the

Pierre Marie Rallu:

store, based on the knowledge of the data we have, what

Pierre Marie Rallu:

computation does, that brings a new set of data, which is the

Pierre Marie Rallu:

presence of the product on the shelf, constantly. And, and the

Pierre Marie Rallu:

idea, the idea is really to be able to change the padding love

Pierre Marie Rallu:

having people which are maybe dedicated to grocery or

Pierre Marie Rallu:

dedicated to GM, that have to do their product, maybe with a more

Pierre Marie Rallu:

versatile workforce in the store, which is more task

Pierre Marie Rallu:

driven, rather than rather than schedule driven.

Mike Graen:

Excellent. So again, I got a text from somebody. So

Mike Graen:

so this may be a little bit a question that you weren't really

Mike Graen:

expecting but I think it's an important one: there are other

Mike Graen:

solutions that are computer vision solutions that either are

Mike Graen:

crowdsourcing, ie go and take the picture and do the analysis

Mike Graen:

there. I'm thinking of things like Field Agent, Trax, etc.

Mike Graen:

There's also a suite of solutions, which are robotics

Mike Graen:

base, you know, Badger robot, Brain robots, Simbe robot, some

Mike Graen:

of those folks who are literally scanning items on the shelf. And

Mike Graen:

reporting that same back, obviously, fixed cameras, is a

Mike Graen:

different solution, walk us through the differences between

Mike Graen:

somebody taking the picture versus a robot catching the

Mike Graen:

picture versus fixed cameras, from your point of view.

Pierre Marie Rallu:

Yep. So there are there for them comes

Pierre Marie Rallu:

in every technology, I think I've been playing with all of

Pierre Marie Rallu:

them. So an island, the fixed cameras, but so when you talk

Pierre Marie Rallu:

about when to take pictures, using your mobile phone, and

Pierre Marie Rallu:

things like that, the advantage of that picture that you have

Pierre Marie Rallu:

the flexibility to have a very neat picture really informed of

Pierre Marie Rallu:

what you want to focus on. So So and then and it's very, it's a

Pierre Marie Rallu:

very light solution, there's not a lot of investment upfront,

Pierre Marie Rallu:

because you don't have to install anything. But you need

Pierre Marie Rallu:

people to do that. And the fact of having the the folks doing

Pierre Marie Rallu:

that work that has a recurring costs, which is extremely high,

Pierre Marie Rallu:

which is the folks taking the picture. And from from most of

Pierre Marie Rallu:

the the brands that have worked with Coca Cola. Cheers to those

Pierre Marie Rallu:

guys. My wife works at Coke so we have some common things

Pierre Marie Rallu:

there, disclaimer. But a lot of the feedback I had is the lack

Pierre Marie Rallu:

of consistency of the pictures. I mean, you gotta take, you

Pierre Marie Rallu:

gotta take the big because yeah, you have an army of people.

Pierre Marie Rallu:

They're just taking pictures. So you need to train them. Taking

Pierre Marie Rallu:

your pictures easy, but taking the right picture. So the AI can

Pierre Marie Rallu:

analyze the right data. I mean, do I have the right frame? Do I

Pierre Marie Rallu:

see everything? Do I Do I Do I Do a corset architect did I miss

Pierre Marie Rallu:

one of the shelf one of the shelfs or something like that.

Pierre Marie Rallu:

And a big one of the issue I've heard about is consistency.

Pierre Marie Rallu:

After consistency. It's not a big deal. If the business case

Pierre Marie Rallu:

is zero, for example, merchandising, because

Pierre Marie Rallu:

merchandising doesn't require as much velocity as inventory. So

Pierre Marie Rallu:

you can have a view of your shelf once a week, once every

Pierre Marie Rallu:

two weeks, and statistically you can start looking at okay, am I

Pierre Marie Rallu:

compliant I might not comply with and things like that. And

Pierre Marie Rallu:

so, for merchandising, especially for the brands, I

Pierre Marie Rallu:

mean, that's what's your show? That seems to make sense. Now.

Pierre Marie Rallu:

There are a lot of brands that we talk to that want more. They

Pierre Marie Rallu:

want to have much more detailed KPIs, they want to understand

Pierre Marie Rallu:

the inventory position of their products. They want to

Pierre Marie Rallu:

understand the dynamic of the product like a heat map. How

Pierre Marie Rallu:

fast is it for like moving during the day, because that's

Pierre Marie Rallu:

what what fix camera can do right there taking pictures all

Pierre Marie Rallu:

the time. So they can analyze, even if the product is out where

Pierre Marie Rallu:

the product moves, whether the product removed and put back and

Pierre Marie Rallu:

creates a heat map of the interaction between the clients

Pierre Marie Rallu:

and the chef. So the effective the effectiveness of the

Pierre Marie Rallu:

merchandising, if you will. So that's one thing. The other

Pierre Marie Rallu:

thing is you mentioned the robots, which on same day, which

Pierre Marie Rallu:

was on my brain, so the robots are so have a great, great value

Pierre Marie Rallu:

in the sense that when they are, first of all, they are very

Pierre Marie Rallu:

close to the shelf, they have a very net and again, they're

Pierre Marie Rallu:

usually they have very nice sensors with good lenses, they

Pierre Marie Rallu:

can, they can then either read the barcode and everything. So

Pierre Marie Rallu:

there are a lot of information associated with orbit and they

Pierre Marie Rallu:

can write continuously in the store that say, a robot will

Pierre Marie Rallu:

give you a picture position once or twice a day at the maximum

Pierre Marie Rallu:

unless you have an army for I don't think that's the point.

Pierre Marie Rallu:

And so and so it's going to give you one or twice a day in auto

Pierre Marie Rallu:

position which is good and as well as merchandising position.

Pierre Marie Rallu:

So I think the part of the part of having the robots is

Pierre Marie Rallu:

interesting is interesting for that perspective, after there is

Pierre Marie Rallu:

the there is the customer perception of the robot in the

Pierre Marie Rallu:

store. Some like some dogs. I mean that that's one thing and

Pierre Marie Rallu:

and the fact that you also have a potential single point of

Pierre Marie Rallu:

failure that doesn't start work at all today. So if you're

Pierre Marie Rallu:

looking for like, if you're looking for like some solution

Pierre Marie Rallu:

that gives you really looking forward to take care of your

Pierre Marie Rallu:

other stocks. I personally think the shelf the shelf eight

Pierre Marie Rallu:

cameras are the best. But if you're just looking for to take

Pierre Marie Rallu:

care of a merchandising, pain points or a branding thing for

Pierre Marie Rallu:

the nose, a solution might work.

Mike Graen:

Well I hope you enjoyed that conversation with

Mike Graen:

Pierre from 1retailAI. Join us next time as we resume the

Mike Graen:

conversation to discuss more about leveraging computer vision

Links

Chapters

Video

More from YouTube