[Music] I've got my good friend Carter McNab here somewhere there is Carter will talk to us about the Hitchhiker's Guide to machine learning and artificial intelligence Carter is a founding member of GRA Australia's premier supply chain consulting firm specializing in supply chain strategy planning and execution over its 20-year history GRA has helped two hundred-plus organisations across multiple industry identify combined savings are more than 10 min billion dollars said a billion gerais focus
ed on practical results delivery and its mission is to turn its clients supply chains into a competitive advantage Carter has over 20 years of international supply chain advisor and transformation experience and has taught at masters level with Monash University logistics and supply chain management program the series of published articles and white papers press quotes and frequent speaking arrangements Carter is recognized as an expert in the field so ladies and gentlemen please welcome cutter
McNab the reason why I've called this a Hitchhiker's Guide to machine learning and artificial intelligence is it's still kind of a nascent topic there's a lot of hype and a lot of excitement the question is what is it where does it fit how does it apply and so this is my best attempt to try to create a little bit of a roadmap for for that looks like I'm betting that it is still early days it's here but it's still an emerging technology so we'll kind of explore that a bit I'm what I'd like to do
is start these discussions with just a quick show of hands it says if you've done anything intentionally with AI or machine learning in your supply chain would you please raise your hand it's funny what I've noticed this doesn't matter how many people in the room it's always two people look I was looking for senators but if it's ten people it's two people if it sounded people it's two people so apparently in any given room so this is machine learning right artificial intelligence dear okay so I'
m before I jump into the kind of the the applications in supply chain let me just make sure this works yeah um I just wanted to point out a couple of things um that sort of underscores the importance of this from a business perspective I also want to make a comment that for made technologies neither good nor bad it's the intention of how it's used that determines actually what the implications are in the world so some of the things I'm in a I'm machine learning I look at it I get a bit of a shud
der it's like oh I don't know about that so it doesn't all sit totally comfortable with comfortably with me but the reason why I'm pointing out is that look it is here and the question is is you know how do we embrace it and deploy it in the way that actually serves humanity as opposed to yeah treating people like people are not like things I think it's very important speaking of people there's a lot of us I remember flipping through a National Geographic several years ago and there was a pictur
e of the National Geographic and a head of graph that kind of went like went like that and what it started at with it said um it was 1 AD so height of the Roman Empire there were 200 million people on the planet and the grass kind of went like this and then it and then it sort of it kind of Galvin and by I think 1880 then we had a billion people so found out you know let's call it 2,000 years later we had a billion and so now it's what's the year again 2019 and we're sort of seven and a bit bill
ion so 1/7 huh you know if the populations increased by a factor of seven times since 1880 there are some people alive who have seen the population triple or quadruple in their lifetime so that's used to say that's unprecedented but I'm pretty sure when I think it was was it so I'm gonna get this probably wrong I think it was like a hundred and twenty five thousand years ago human beings got down to apparently 30 30 pairs so it's about 60 Homo sapiens left southern Africa all of us are descendan
ts from those people and in fact if you trace our mitochondrial DNA back we all come from one of seven women so we are actually literally all related it is it is a big family believe it or not it's just it's the truth but so why am i pointing this out oh then I guess the other point is that at 2045 it's supposed to level off about around 9 billion but keep in mind that there's no more water there's the same amount of water there's the same amount of resources and we are consuming much more than
we used to so not only is there an exponential increase in population there's an exponential increase in consumption business business might say that's wonderful the sustainability of you might say that's concerning but I think our challenge is we have to find a way to bring economical and ecological considerations together they can't be in opposition they can't be separate because they're quite intertwined so they'll look there are a lot of us running around the next one I make is and we leave
a giant wake of data with us as we run around these days so this was another National Geographic magazine article have just taken a scan of it and this was several years old but this was an article describing what MIT labs could predict with a very high degree of accuracy just by looking at search engine behavior and you know one of the bubbles on there says I'm pregnant and doesn't know it yet so they were able to work out if someone was pregnant by just observing changes in search engine behav
ior and again this was they were able to detect this before the person who was pregnant recognized it now that's interesting again is that good or bad oh you know sort of depends depends on how that's used but this is the the level of insight that can be generated from day two these days and again this was a few years old and again this is proliferating quite exponentially so we've got a lot of folks running around a lot of data as well and then on top of that in the world some of us live in is
the supply chain we're old I'm not even going to come close to going through those individual dots bit by bit but the other point is supply chains have got a lot more complex in some ways supply chains if it got more fragmented more granular more particulate we've got many many more sourcing options than we used to and if you look at the number of fulfillment options and possibilities we have now than what we had say 10 or 15 years ago it's just kind of been an explosion product proliferation sh
orter life cycles more trends more competition you've heard all that before but I guess what I'm saying is that the task and try to manage all this is getting a little bit more challenging and I think that's why something like machine learning and its possibilities may become a fundamental way that we do things moving forward because with that amount of data with the amount of options and complexity that there is in supply chains um the ability to efficiently extract an insight from all that dat
a becomes a really key point um it is going to change the way we work I mean I've been asked the question a few times well you know because we're actually seeing rolls the swells at another talk a couple weeks ago there's a guy from a recruiting company said he said we're seeing requests for these sorts of roles and I said what is it he said it's a supply chain design architect I said what do they do he said of people that I said they have to have a what said is a mathematical understanding of h
ow to solve complex supply chain problems strategic insights and and you know business contest macroeconomic considerations they have the ability to understand warehouse and DC layout designed based on fulfillment options they need to understand the different automation technologies build a business case and see a suit implementation I said if you've got anybody like that said no yeah it does like it either way I mean because I I've never met one person who has all those skills it's I just haven
't seen that yet not at a suitable level of depth so I know there's a lot of interest in like recruiting of data scientists and these sorts of things I'm again a good skill set but remember that you know maths is a maths is a philosophy it's the language statistics there's a science built on the language of maths so just because I'm good at working with numbers doesn't mean I understand the art of its application in a particular industry so it's good to have a data science it's better to have so
meone who understands how to use data to solve a problem and has industry experience and knowledge but I think all that stuff is important and look it is a disruptive technology and I'll show you some of the examples here with a couple little videos which give me a break and take the attention off B for a little while which believe it or not do like so what is a on machine learning at a really high level it's a it's a it's a mathematical construct that looks for relationships in died kind of cre
ates a model and uses that for future prediction the another way of saying that it's it's something that looks at the relationship between correlation and causation so so I'll do some more artificial intelligence and machine learning right now I can deduce clearly that breakfast presentations create darkly colored jackets I mean it's it's it's actually triggers correlation here right we're all here at a presentation and there's a lot of people wearing dark clothing so they're for breakfast prese
ntations so if I were to set another breakfast but I can expect to see lots of darkly colored clothes right yeah I mean so there's a correlation but did it cause that so that's that's one of the the tests with these things is is the data actually meaningful in terms of actually a predictive piece and machine learning is trying to establish those sorts of things the relationship between correlation and causation one of the things that's exciting about it is that having done a lot of work and supp
ly chain design and planning you know a lot of times what we're told with you know forecasting and planning is you know it's great to run a promotion on this item but I have a sense that you know a few weeks later the whole category takes a hit like in other words it's not just so yes the promotion worked I call that vertical I'm just this is how I think and I look at that like it's a vertical issue but when I dropped that vertical issue in the water it creates horizontal ripples and the rest of
the product range and historically we haven't had a really great way of analytically dealing with that machine learning now and I I gives us the ability to understand a broader context because really what it's doing is it's looking at multiple data sets that don't have to be formatted the same way they can be disparate but as long as there's a consistency between the data sets it's looking for relationships and saying AHA these are the things that actually make a difference and now that I know
that I can focus on it the other thing about machine learning is that it can be very data hungry so you don't necessarily want to try to boil the ocean every time you want to make a piece of toast you know the trick is what are the things that are actually relevant so a lot of the idea with proof of concept in with machine learning is to kind of figure out what really matters we did some work with a convenience retailer and you know it was something around what happens when you change the price
of the 1.5 liter when you bring it down what we started to see as people would switch out of the 600 mill and start buying the 1.5 but there are 24 different permutations of price points and so long in relationships we found only two of two of the 24 mattered only two of the 24 actually so then now we know where to spend our time we're not worried about all 24 of those just as a couple so what are we seeing in the market I'm very much still in the innovation cycle in the sense that you know it's
it's kind of a new shiny thing it is exciting but without what I offer is that machine learning and AI isn't an opportunity to skip steps so in other words it's like we don't have this capability so we'll just do a on machine learning and that'll solve the problem I kind of describe and mache I'm machine learning is like the top of the wedding cake you have to have all the other layers before it really starts to add value and I'll explain a little bit more about what I mean in a minute but stil
l early on but supply chains are data rich they can get data from lots of different points and this is the one of the challenges I find with a machine learning is that there are so many possibilities and fewer eventualities right now I think that will change but what I want to do today is kind of try to frame that up just to give you sense of that landscape so in terms of this is just kind of one of our views of how we see supply chains there's a lot of information on it I like to kind of think
of this at three chunks there's a strategic element which basically says I know my business strategy what my customer offer is I can then come up with my network strategy and build my supply chain based on the business strategy and the customer value proposition in fact they should be linked because my customer value proposition should inform my supply chain structure so at a strategic level that's that's kind of that piece generally speaking decisions at that level tend to be longer term they t
end to be higher level and the data that we use tends to be less granular it's less detailed right because I'm trying to make a decision for 15 years - now I'm not necessarily concerned how long it takes to drive from the street to this street at Tuesday at 9:20 in the morning for this particular problem so it's a design question the integration I just talked to because it's there but the integration pieces then the organizational constructs that are required to bring this stuff to life so yes a
nd if he processes your roles and responsibilities and policies and so on but I'm not gonna spend much time on that the next level is kind of the planning levels so I've got my supply chain but now I need to plan it so forecasting inventory planning punishment planning snop transportation planning and so on and again there tends to be again more data that I use it tends to be more sort of short to medium term whereas then I drop down to the execution section just really around you know looking a
t warehouse fulfilment we're asking processes manufacturing processes and so on I'm thinking of starting to get a lot more granular much shorter term horizon but a lot more granular so I just kind of framed that up in terms of those three those three kind of horizons or three levels and then how it fits in I guess the interesting thing is we pulling the presentation together because literally it was just like Oh what would you like to present why don't we do this and we kind of spelled it out an
d the team started looking through it and the funny thing that we found is there's not a lot of great examples of machine learning and AI in the strategic realm there's some in the planning a lot more in the execution but not much in the strategy piece yet that doesn't mean it isn't coming it's just not as well developed so jumping into that if we look at those three horizons and this is what are some applications what might they be the other thing about this is get creative and start maybe thin
king about this in your own organization the way I look at this is do you have a hunch that something may be related to something else and you've always kind of mount I bet these things are relighted or you know and we do this this sort of thing happens because it's really interesting to then try to get that data and do a proof of concept with AI machine-learning to see if that actually if the hypothesis is true and you can kind of proof of concept and do it in sort of a in a controlled way but
one might be population and demographic data to pre position inventory and strategic locations there was an article in the AFR I'm sorry I'm just gonna have to say this I didn't mean no offense I acknowledge that it may cause it but the fact that the AFR has a title it says well of us learns not to mess with the clintons love of Doritos and this is what we're using I am machine learning for sometimes I just have to chuckle like really that's okay but the point point about this was is that if you
really look at demographics and you really look at preferences and I guess supermarkets have been doing this for a while which is kind of regional or kind of locale based ranging but really starting to get some of those customer on preference attributes and using that to actually come up with the stockmen policy so not just a man planning not just an allocation process but what we're actually saying and it kind of dynamically range that fits in a particular demographic market that's that's one
of the applications that we're seeing there so that's happening another one might be I'm you know if you're doing network planning or modeling the way that we've done this historically is you know what's the business strategy what's your CVP and then what are the scenarios well what happens if revenue goes up by forty percent what if it stays the same what if it goes down by 40 percent and so we usually put a bunch of what-ifs in there to kind of see how robust the the recommendation is and so t
hat kind of gives us a sense for it sensitivity but generally those inputs are guesses so those are best guesses right so what if we now can start using machine learning to inform some of those hypotheses about the sorts of scenarios that we're gonna say what about population growth what about the income in those populations what about the preferences in those populations now let's tie build that into our offer moving forward okay what about things like as well the projected congestion in the ne
twork as the population increases and what does that say about delivery times in the CVP might we then change the model from a DC fulfillment to a dark store idea because of the density the location and the expected real estate prices so these are the sorts of things we might start bringing into the strategic realm this is an example I mean and it's interesting a lot of this stuff what I've seen is a lot of the stuff is already being used in in agriculture for yields why is that I think one of t
he reasons for that is because I think the relationship between correlation and causation is much clearer nutrients in the soil sunlight water levels I mean it's it's pretty clear that these things are related and relatable so what you're seeing on the slide we've got live sensor data for example that talks about optimal harvest times and this is happening so we can look at you now recent rainfall are the conditions right for harvest off we go six months ahead projected weather changes will impa
ct the harvesting time line so we can start making adjustments six months out maybe twelve months out we're saying we're lower than expected yield rates we might change our labor scheduling the workforce sort of distribution and then commodity prices over 24 months might be changing so that might impact the decisions were making now and a little kind of graphy thing that's moving around is actually showing the yield over a period of time based on a machine learning approach so interesting a lot
of the more strategic ones they've seen so far have been more in agriculture and it kind of makes sense to me while planting we've done some work ourselves in this planning is really now more if we talk about our set say our forecasting demand planning in the toy planning and so on what I said before is is a great example is this notion if I run a promotion what's the net effect on all products not just on the one I'm running the promotion on so what's the net impact of a particular piece and im
agine the power of that now and say a thought process you know as opposed to just looking at it as a vertical issue it's a horizontal issue one of the tool sets we work with in the US is integrated with I'm Fred which is the Federal Reserve Economic database and what it's doing it's looking for relationships and changes for things like interest rates physical planet policy monetary policy housing starts and so on and then looking for as these things change is there anything does it look like it'
s having a correlation in other words an extrinsic impact on the demand and as it starts learning from that as we start to see things changes the system's start to make automatic adjustments now we can start actually getting some real data around when we make pricing changes how does that actually impact things again that was pretty hard to do in the past because they're multivariate they're nonlinear you know and we just really haven't had great mass to kind of solve those problems but that's t
hat's now here I think is around Network inventory optimization which would say I've got five locations I want to have a effective 99.9 percent in stock position for the network one way of doing that is holding inventory at 99.9 in all five locations you guys know the inventory versus service and falls curve that it gets exponential at that you know those last few percentage points so the point is well hold on a second if I've do I need to do that or could I hold 95 percent in all 5 locations wh
ich means that my probability being out of stock is 0.05 two v minus one which means I get a basically a 99.9% service level and it means five percent of the time I'm distributing from a non optimal location but on a total cost basis that's the that's the lower option so we're kind of getting into these sorts of capabilities that next level of refinement kind of cost out another one is planning process automation we're seeing that some of these demand planning tools are actually learning they'll
actually learn from planet behaviors so how do we how we filling order so we've got a recommend an order but are we are we rounding up to an inner or to an outer or we tried to build full containers or pallets how we doing that and again over time it'll learn but the other thing about this is doesn't mean it necessarily has to do the work for but it can actually make a more informed recommendation as this is what we think you would likely do because this is what you have been doing and this is
what we've prepared for you or you can automate it to say that for you know four orders less than a certain dollar value that have good forecast accuracy whatever get automatically approved so we don't have to look at those so there are some options there another area we're seeing some development is again another place that's kind of been a black art which is new item introduction and NPD so what are all the conditions around a new item Lodge because again we typically don't have great history
that historical approaches have been coffee history from a like set of items bring it over learn from that but again how the machine learning will start to take all that into account I mean bring that in now here's the this is that this is the bit that I think is kind of fun the research is and there's I've got several University white papers on this that we're done by mathematics departments is the bottom line is if you run machine learning by itself against a historical data set versus kind of
the traditional forecasting techniques the traditional forecasting techniques do better so I thinking about maths remember it's it's it's it's it's always horses for courses and what the best analogy that I've come up with so far I'm sure there's a better one is that if you get a block of land and it's covered in trees but you want to build a garden do you get the gardener or the landscape or landscaper to get rid of the trees so machine learning is a subtle process of refinement it's actually
very sensitive it's very subtle so I don't want to use machine I to do my base forecasting in fact I've talked to several companies that have tried this and changed because they said it made it worse I talked to one of the big grocery retailers and they said we're still using our existing forecasting approach for our forecasting but we're using a I machine learning at a store level to look at foot traffic during the day weather patterns and a few other things to then figure out what we need to d
o in the store that day so again very short-term horizon so it's not a replacement for it's an it it's in in addition to I just want to make clear so you don't get to skip steps we don't really do good for us testing so we'll just do all machine learning and we're right is the first point second point is like AWS Amazon Web Services has an AI and machine learning engine so they say throw us your data we'll give you a forecast back have a think about that what does amazon do they sell products bu
t are they asking for data on your sales history ever think but what I'd be saying is also be aware that it's you need to be very careful about what you're using it for I would not recommend using it for your base forecasting there's a lot more in the execution space so a lot more because again we're getting to this kind of lower level what I might do is just show you a couple of videos but we've got things like IOT sensors that are giving us real-time information to help us with predictive main
tenance as you know it's a good example autonomous vehicles and this is the area we're starting to see the AI and automation really come you know kind of marry up so this is one on you know shipping using AI which is saying that if I start to understand that you know chance of Freight being delighted in Shanghai what might I do was a rerouting option there's a tropical thunderstorm that's going to be happening off the coast of Thailand maybe we should switch to air freight for this particular le
g so again it's starting to look at weather patterns and saying what will that actually mean for delivery and what our options show you a video real quick it's no longer a choice supply chains must digitally transform to gain a competitive advantage the key to that advantage is visible despite decades of trying nobody has gotten the visibility they need why is that because until clear metal no one has been able to make sense of the underlying data clear metal has solved this problem with modern
ingestion machine learning and AI we're the only provider that delivers the visibility you need and can trust forget all the marketing hype buzzwords and misleading promises shippers around the world are using clear metals visibility to increase revenue and drive down costs we help optimize inventory proactively manage exceptions reduce transportation expenditures and establish a competitive advantage the future of supply chain is data intelligence the future of visibility is clear metal that's
not an endorsement of that particular offering I'm just giving an example of what they're some of the shippers are now putting forward as the point of difference I'm I haven't used that so I have no financial links to that organization whatsoever we're we're also saying it is in some of the smart storage systems so some of you may have seen auto store so why waste time on shelve-based solutions when autostore is here autoStore is a cube based system making use of all space for proper warehousing
turn that wasteful air into storage and double triple or even quadruple the inventory capacity without moving to a new building bins are stacked right next to eachother on top of each other radio-controlled robots drive on tracks above the cube lifts down to grab bins and deliver them to workstations for order fulfillment or replenishment all operations get done efficiently and accurately in high-speed workstations it's a cube based storage mechanism that works basically in three dimensions it
works horizontally and vertically but there's an AI algorithms that are actually driving the automatic cuz it's automatically relaying itself you know as it's proceeding and and and and dispatching so there's AI driving that now this is um you've probably maybe some of you guys have seen the Boston Dynamics robot now this is still a prototype but this is a picking a robot kind of cuddly aren't they basically what I'll say is this is that thinking away into this there's a lot of question about ho
w do we put our towel in the water and that is something that's the answer is it is a toe in the water approach is is really start with hypothesis you probably already have an intuitive sense for there's something in the business that if I had if I could relate these and make meaning out of it and could use it to predict that it might add some value so it's create the hypothesis develop of proof of concept and in the creative concept then you can start to see what things actually do make sense w
hat is relatable what does add some value you can then make the business case for it refine the model and then look to implement and integrate so you kind of do that in a controlled way and make sure it's it's safe and you're looking at the right things at the right amount of data and again the final point I'd make on this is that I mean again technology is neither good nor bad it just is it's the intentions of how we try to use it or how we how we intend to use it um I wish you all wonderful an
d humane intentions and how you use technology and good luck and thank you for your time you
Comments