vermorel 4 days ago | flag | on: Let's try Lokad

By the way, mathematical formulas are pretty-printed as well:

$$ \phi = \frac{1 + \sqrt{5}}{2} $$
vermorel 4 days ago | flag | on: Let's try Lokad

I have just updated Supply Chain News to pretty print Envision scripts as well. Here is the first script:

montecarlo 1000 with // approximate π value
  x = random.uniform(-1, 1)
  y = random.uniform(-1, 1)
  inCircle = x^2 + y^2 < 1
  sample approxPi = avg(if inCircle then 4 else 0)
show scalar "π approximation" with approxPi // 3.22

A discussion with Jay Koganti, Vice President of Supply Chain at Estée Lauder’s Centre of Excellence

vermorel 3 months | flag | on: Architecture of Lokad

The predictive optimization of supply chain comes with unusual requirements. As a result, the usual software recipes for enterprise software aren't working too well. Thus, we had to diverge - quite substantially - from the mainstream path.

The 5 trends as listed by the author:

  • 88% of small businesses supply chains will use suppliers closer to home by next year.
  • Small business supply chains are moving most or all suppliers closer to the U.S. faster than predicted
  • The strained economy and low inventory are top stressors
  • Software-based emerging tech is on the rise while hardware-based ones lag behind
  • 67% of SMB supply chains say their forecasting techniques were helpful in preventing excess inventory

This problem is referred to as censored demand. Indeed, this is not the sales but the demand that is of interest to be forecast. Unfortunately, there is no such thing as historical demand, only historical sales that represent a loose approximation of the demand. When a product goes out of the assortment, due to stockout or otherwise, sales drop to zero, but demand (most likely) does not.

The old school approach to address censored demand consists of iterating through the historical sales data, and replacing the zero segments with demand forecast. Unfortunately, this method is fraught with methodological issues, such as building a forecast on top of another forecast is friable. Furthermore, in the case of products that are not sold during for long periods (not just rare stockout events), say summer, forecasting a fictitious demand over those long periods is not entirely sensical.

The most commonly used technique at Lokad to deal with censored demand is loss masking, understood as from a differentiable programming perspective. This technique is detailed at:

Hope it helps, Joannes

There are several questions to unpack here about seasonality. (1) Is seasonality best approached as a multiplicative factor? (2) Is seasonality best approached through a fixed-size vector reflecting those factors? (hence the "profile") (3) How to compute the values of those vectors?

Concerning (1), the result that Lokad has obtained at the M5 competition is a strong case for seasonality as a multiplicative factor: The literature provides alternatives approaches (like additive factors); however, this don't seem to work nearly as well.

Concerning (2), the use of a fixed size vector to reflect the seasonality (like a 52-week vector) has some limitations. For example struggles to capture patterns like an early summer. More generally the vector approach does work too well when the seasonal pattern are shifting, not in amplitude, but in time. The literature provides more elaborate approaches like dynamic time warping (DTW). However, DTW is complicated to implement. Nowadays, most machine learning researcher have moved toward deep learning. However, I am on the fence on this. While DTW is complicated, it has the benefit of having a clear intent model-wise (important for whiteboxing).

Finally (3), the best approach that Lokad has found to compute those vector values is differentiable programming. It does achieve either state of the art results or very close to start of the art with a tiny fraction of the problems (compute performance, blackbox, debuggability, stability) associated with alternative methods such as deep learning and gradient boosted trees. The method is detailed at:

Hope it helps, Joannes

Patrice Fitzner, who contributed to the design of the Quai 30, a next-gen 21st century logistical platform explains the thinking that went into this 400m by 100m monster of automation.

Very nerdy Factorio rocks

Just to clarify the terminology that I am using the following: the EOQ (economic order quantity) is a quantity decided by the client, the MOQ (minimal order quantity) is a quantity imposed by the supplier. Here, my understanding is that the question is oriented toward EOQs (my answer below); but I am wondering if it's not about picking the right MOQs to impose to clients (which is another problem entirely).

The "mainstream" methods approach EOQs, especially all of those that promise any kind of optimality suffer from a series of problems:

  • ignore variations of the demand, which is expected to be stationary (no seasonality for example)
  • ignore variations of the lead time, which expected to be constant
  • apply only to "simple EOQ" that apply to a single P/N at a time (but not to a EOQ for the whole shipment)
  • ignore macro-budgeting constraints, aka this PO competing against other POs (from other suppliers for example)
  • ignore the ramification of the EOQs across dependent BOMs (client don't care about anything but the finished products)

Do not expect a formula for EOQs. There isn't one. A satisfying answer requires a way "to factor in" all those elements. What we have found at Lokad for better EOQs in manufacturing (not "optimal" ones, I am not even sure we can reason about optimality), is that a certain list of ingredients are needed:

  • probabilistic forecasts that provide probability distributions at least for the future demand and the future lead times. Indeed, classic forecasts deal very poorly with irregular flows (both demand and supply), and MOQs, by design, magnifies the erraticity of the flow.
  • stochastic optimization, that is the capacity to optimize in presence of randomness. Indeed, the EOQ is a cost-minimization of some kind (hence an optimization problem), but this optimization happens under uncertain demand and uncertain lead time (hence the stochastic flavor).
  • financial perspective, aka we don't optimize percentages of errors, but dollars of error. Indeed, EOQs is typically a tradeoff between more stock and more overhead (shipment, paperwork, manhandling, etc)

In my series of supply chain lectures, I will be treating (probably somewhere next year) the fine print of MOQs and EOQs in my chapter 6. For now, the lecture 6.1 provides a first intro into the main ingredients needed for economic order optimization, but without delving (yet) into the non-linearities:

It will come. Stay tuned!

vermorel 5 months | flag | on: Goodbye, Data Science

An incredibly perceptive discussion that reflects my own experience with data science in general.

vermorel 5 months | flag | on: Cycle Count Manager

A small side software project dedicated to inventory counting.

The earliest occurrence I could find of the concept is 2016 with the presentation:

The 2018's book is available at:

vermorel 5 months | flag | on: The Saga of Supply Chain Innovation

ATP (used in the article) stands for Available-To-Promise.

I am very much in agreement concerning the list of stuff that didn't work: Consolidations Decimated Value, Consultants Failed to Deliver Value Through Software Models, Barney Partnerships Bled Purple, not Green, The Saga of Venture Capitalists and Private Equity Firms, New Forms of Software Marketing Creates Haze not Value

Concerning the value of cloud and NoSQL. Well, yes, but it's a bit of an old news. Lokad migrated toward cloud computing and NoSQL back in 2010. A lot did happen since then. For a discussion about what a modern cloud-based tech look like

vermorel 5 months | flag | on: Prioritized Ordering [video]

A couple of relevant links:

In most of Western Europe, my (tough) take is that, career-wise, those certifications are worth the paper they are printed on. The vast majority of the supply chain executives that I know have no certification.

More specifically, the example exam questions are ludicrous, see

MCQ (Multiple Choice Questions) is the exact opposite of the sort of problems faced by supply chain practitioners. MCQs emphasize super-shallow understanding of vast array of the keywords. Worse, it treats those keywords (eg data mining, integer programming) as if they were encompassing any kind of cohesive body of work (or tech). This is wrong, plain wrong.

vermorel 6 months | flag | on: Supply Chains are Healing

Minor: Edited the title to avoid the question mark. I am trying to reserve the question titles to actual questions addressed to the community.

Light retrospective on the evolution of Amazon automated decision-making tech for supply chain. Interesting nugget, Amazon appears to be still using their multi-horizon quantile recurrent forecaster (1) as it appears to have taken several years to cover the full scope (which is not unreasonable considering the scale of Amazon).

(1) A multi-horizon quantile recurrent forecaster
By Ruofeng Wen, Kari Torkkola, Balakrishnan (Murali) Narayanaswamy, Dhruv Madeka, 2017

The book can be purchased from

The main message by Schuh et al. is that a collaborative relationship with suppliers can be vastly more profitable that an oppressive one solely focused on lowering the supply prices. While the idea isn't novel, most companies still favor aggressive and antagonistic procurement strategies which leave no room for more profitable collaborations to emerge.

10 years ago, Amazon was acquiring Kiva Systems for $775 million.

The quote is from The Testament of a Furniture Dealer by Ingvar Kamprad, IKEA founder. The original document can be found at:

Forecasting and S&OP initiatives almost invariably turn into bureaucratic monsters.

A team from Lokad took part in the M5 competition. The method, which landed No1 at the SKU level, has been presented at

vermorel 7 months | flag | on: Software to simplify the supply chain

Interesting nuggets of this interview with Ryan Petersen, CEO of Flexport:

- 20% of the Flexport workforce is software engineering. The rest is sales and account management.
- The P95 transit time is a 95% quantile estimate of the transit time; part of the core Flexport promise.

Overall, a very interesting discussion, although the simplify part really refers to the Flexport product itself.

Most supply chain initiatives fail. Dead-ends are a given, although my understand differs a little bit concerning the root causes. Among the top offenders, the lack of decision-centric methodologies and technologies ranks very high. In the 'future' section proposed by the author, I see layers of processes to generate ever more numerical artifacts (eg: Market-driven Demand, Demand Visibility, Baseline Demand and Ongoing Analysis of Market Potential, Unified Data Model Tied to a Balanced Scorecard, Procurement/Buyers Workbench).

vermorel 7 months | flag | on: puts itself up for sale

A decade ago, - along with a couple of similar ecommerces - took extensive advantage of the payment terms of their oversea suppliers (mostly in Asia). Their supply chain execution allowed them to sell their goods while goods were still in-transit. This worked well for furniture as customers - at the time - were OK waiting a month or two to receive their order. I don't know where they stand now, but I suspect that the supply chain tensions (sourcing problems in Asia + surge of transport fees) do pose significant challenges to this business model.

My previous take on safety stocks:

In short, not only the normal distribution assumption is bad, but the whole approach is very naïve. It made (somewhat) sense before the advent of computers, but at present, safety stocks should be treated as a method of historical interest only.

vermorel 7 months | flag | on: Differentiating Relational Queries

This work is done by Paul Peseux who is currently doing a PhD at Lokad. In terms of research, it's a convergence between machine learning, mathematical optimization and compiler design; fields that are usually considered as fairly distinct - but that end up being glued together in the context of differentiable programming.

vermorel 7 months | flag | on: Demand sensing [pic]
impossible to get a real sense of what's offered without some sort of PoC

Fully agree. This is why I abhor those made-up terminologies: it's pure vendor shenanigan's.

vermorel 7 months | flag | on: Demand sensing [pic]

Q: Why a new buzzword if it's about repackaging techniques that already have proper names?
A: Occam Razor: to make the tech appear more attractive and valuable than it really is.

According to [1], SAP recognizes 'demand sensing' as 'a forecasting method that leverages [...] near real-time information to create an accurate forecast of demand'.

  • Why would a 'near real time' provides a forecast that is any less accurate than a batch forecast happening with a lag of, say, 10min?
  • Why should gradient boosting be even considered as a relevant technical solution for 'near real-time' tasks?

Remove demand sensing from the picture, and you still have the exact same tech with the exact same processes.


When I look at the market, I see major contributions of GroupThink:
- Failure of IT Standardization. SAP and IBM failed the market. The recent gains in market share of Kinaxis, o9, and OMP are largely due to the failure of SAP to drive thought leadership in planning.
- Private Equity M&A. Software mergers & acquisitions also slowed innovation. The technology roll-ups of INFOR, JDA (now BlueYonder), and E2open improved investors’ balance sheets, but did not drive value for their clients.
- Event Companies Are the Nemesis of the Industry. Event companies take large sums of money from technology companies and host events based on the Rolodex of a prior supply chain leader

A spot-on analysis. Low level IT standardization is moving forward nicely (think federated identity management), but it's not the case for high level IT (think workflows). The success of products like Tableau reflects that there is a major need to cope with the lack of standardization.

M&A in enterprise software is almost always resulting in large about of technological debt. It's very hard to get good software engineers motivated about clean-up millions of lines of code of haphazard codebases where stuff has just been "thrown together".

Event Companies are a severe form of epistemic corruption. I discussed the case in

The sheer scale of this piece of engineering is incredible. We are talking of a machine that is 400m x 100m x 12m big. The whole thing maximizes that can be done in terms of inventory storage and inventory throughput while taking advantage of every cubic meter that is available.

Digital talent remains the Achille heel of many (most?) supply chain initiatives. Nonsensical tech decisions keep being made due to a lack of understanding of what is at stake. The challenges pointed out in this post a few years back have only become more acute since then.

The stochastic gradient descent (SGD) is used for a whole variety of supply chain problems from demand forecasting to pricing optimization. From a software performance perspective, the crux of the SGD problem is to increase the wall-clock rate of descent while preserving the determinism of the execution. Indeed, as far as parallelization is concerned, indeterminism is the default; it takes effort to achieve a reproducible flavor of the algorithm. The report introduces a technique that delivers a 5x speed-up at a 6x increase of compute costs.

10 years is a good ballpark assessment to produce a good software product - assuming there are people who will stick around for a decade to see it through. See Written 20 years ago, but the points are still largely valid.

vermorel 7 months | flag | on: Conformal prediction materials

Conformal predictions are one of the flavor of probabilistic forecasting, leaning toward high dimensional situations. This repository is an extensive compilation of the papers, phds and open source toolkits that are available for conformal predictions.

We strongly believe that probabilistic methods play a key role in the future of supply chain planning. They represent the right way to go for areas that contain uncertainty, including for all types of forecasting and the subsequent planning situations.
Traditional deterministic planning methods base their decisions on the mistaken assumption that uncertain values can be approximated by a single average number. As a direct consequence of this assumption, plans are often infeasible at the time they are created and manual interventions are continuously needed.

Better late than never! However, let's immediately point out that the SAP IBP architecture is very much hostile to probabilistic modeling. More specifically, the high memory consumption of HANA is going to add some massive overhead on top of methods that not exactly lightweight in the first place.

vermorel 8 months | flag | on: Proxy Variable [pic]

Service levels are probably the favorite proxy variable in supply chain. Supply chain textbooks and consultants assume that "finely tuned service levels" automatically translate into better outcomes for the company, while those service levels say very little of substance about the quality of service actually perceived by customers.

Supply chains are complex systems. It's maddeningly difficult to solve problems rather than displacing them. When confronted with incredibly difficult problems, bureaucracies are also incredibly good at ignoring them altogether. In supply chain, big problems are usually big enough to take care of themselves.

How far should we go to say that we have reached a point of say realistic representation of an agent? Also when we say accuracy , what does it really mean?

Right now, as far as my understanding of the supply chain literature goes, there is just nothing yet published to tell you whether a simulation - in the general case - is accurate or not. The tool we have for time-series forecast don't generalize properly to higher dimensional settings.

For example, if a simulator of a multi-echelon supply chain of interest is implemented, and then someone decide to refine of the model of some inner agent within the simulator, there is no metric that are even known to be able to tell you if this refinement is making the simulator more accurate of not.

Stay tuned, I am planning a lecture on the subject in the future, it's a big tough question.

Lokad tries to push a lot of (hopefully) quality supply chain materials in the open. Unlike many vendors, we don't attempt to shroud our technology in a veil of mystery. However, we need backup. If you think that you help us produce videos, guides, articles ... then, drop your resume at

Answering a question on YouTube:

As per my understanding the following are the core concerns -
1) Accuracy
2) Doesn't necessarily represent reality based on Agent behaviour
3) Gives me insights, ok now what should i do? Don't give me numbers, tell me what to do. If an employee sits down and tweaks parameters then how do i make sense if the decision is correct?

Yes, in short, the two big gotchas are (a) your digital twin may no reflect the reality (b) your digital twin may not be prescriptive.

Concerning (a), measuring accuracy when considering the modeling of a system turns out to be a difficult problem. I intend to revisit the case in my series of supply chain lectures, but it's nontrivial, and so far all the vendors seem to be sweeping the dust under the rug.

Concerning (b), if all the digital twin delivers are metrics, then, it's just an elaborate way to waste employee's time, and thus money. Merely presenting metrics to employees is suspicious if there is no immediate call-to-call. If there is a call-to-action, then let's take it further and automate the whole thing.

Indeed. Although, as aircrafts get dismantled, it tends to introduce a lot of spare parts into the market. Thus, most of the time, the parts of weaning aircraft types become cheaper despite the lack of production of parts. However, as you correctly point out, there are parts that become rare and very expensive, making the aircraft type economically unviable.

A nice illustration the sort of stuff that characterizes aviation supply chain: aircrafts are both expensive and modular. Thus, the option is always on the table to take a component from an aircraft and move it to another aircraft. Most of time, exercising this option is pointless, but sometimes, it's an economically viable move. Here, this is what Boeing is doing with aircraft engines. Aviation supply chains are not about picking safety stocks :-)

Fun fact: Lokad started to implement digital twins of supply chains more than a decade ago; although I don't overly like this terminology. As a rule of thumb, I tend to dislike terminologies that try to make tech sounds cool, irrespectively of the merit of said technology. There are tons of challenges associated with large scale modeling of supply chain, the first one being: how accurate is my digital twin? Tech vendors are usually exceedingly quite about this essential question.

747 have been produced for 54 years. The one most notable evolution being the introduction of the fly-by-wire tech in the 1990s

This plane has massively contributed to the democratization of both air travel and air shipments. Considering that aircrafts are typically operated for decades, some 747 are likely to keep flying for the next 20/30 years.

Lion Hirth is Professor of Energy Policy at the Hertie School. His research interests lie in the economics of wind and solar power, energy policy instruments and electricity market design.

The document introduce marginal pricing - in the context of energy, and make three statements about it:

Marginal pricing is not unique to power markets.
Marginal pricing is not an artificial rule.
If you want to get rid of marginal pricing, you must force people to change their behavior

Three points are very much aligned with what is generally understood as mainstream economics. Those points are quite general and do apply to most supply chains as well.

I am not familiar with the specific Greek energy market.

However from a supply-and-demand perspective,

  • Intermittent energy sources do not meet the Quality of Service requirement which is essential for energy.
  • As long as the source can be turned into electricity, all energy sources are near perfect substitutes. Hence, one cannot isolate the price of a selection of sources vs the rest.
  • When demand is inelastic and grows, as it is the case for energy demand, it's the supply that has to grow.
vermorel 8 months | flag | on: Lokad is hiring a Supply Chain Scientist
The Supply Chain Scientist delivers human intelligence magnified through machine intelligence . The smart automation of the supply chain decisions is the end product of the work done by the Supply Chain Scientist.

Excerpt from 'The Supply Chain Scientist' at

Transit costs to low orbit are still beyond the realm of supply chain, however, it is notable the cost per kilogram has been going down by a factor 1000 over the course of 70 years. If progress keeps happening at the same pace, in a few decades, launches will become an option. The benefits of easier access to low orbit are somewhat unclear beyond telecommunications, but specialized micro-gravity factories has been explored many time in science fiction. At this point, orbit remains too expensive to even try to investigate newer / better industrial processes in orbit.

vermorel 8 months | flag | on: How to Measure Forecastability (2021)

The only way to assess "forecastability" of a time-series is to use a forecasting model as a baseline. This is exactly what is done in the article, but unfortunately, it means that if the baseline model is poor, the "forecastability" assessment is going to be poor as well. There is no work-around that.

Stepping back, one of the things that I have learned more than a decade ago at Lokad is that all the forecasting metrics are moot unless they are connected to euros or dollars attached to tangible supply chain decisions. This is true for deterministic and probabilistic forecasts alike, although, the problem becomes more apparent when probabilistic forecasts are used.

Be our guest, virtually! These live, one-hour tours take you behind the scenes at our fulfilment centres, using a combination of live streaming, videos, 360° footage, and real-time Q&A to replicate the experience of our in-person tours.
Live virtual tours are approximately 1 hour long, including Q&A.
Registration closes 6 hours in advance of each tour. Last-minute registration ("instant join") is not possible. Tours will no longer appear in the calendar once registration is closed, or when they are fully booked.

Various options are available depending on the region of interest:

Steps for the new supply chain decision systems:

  • Pick expensive consultants to devise a 100 pages RFP. Gather all requirements, especially the imaginary ones.
  • Select 20 vendors, shortlist 2 ultra-expensive big names plus 1 cheap startup (they won't make it to the final round, but those guys are more fun to talk to)
  • Pick the big name vendor that has the most features. An excess of 1000 screens is desirable.
  • Plug the latest bleeding edge AI toolkit. The important part is the "bleeding" part, that's a sign of real innovation.
  • Customize all UIs so that everything becomes collaborative. Numbers were bad before, but now, it costs a fortune to produce them.
  • After 6 months, declare the initiative a success, and change job immediately afterward.

Simple, really.

vermorel 8 months | flag | on: Future-proof your supply chain

The article proposes three ways, namely:

Building supply chain resilience by managing risk
Using technology to increase supply chain agility
Identifying and promoting ways to be more sustainable

However, the analysis is a bit all over the place.

  • For risk management, the example of RFID at Nike is given. However, RFID has nothing to with with risk management at the supply chain level.
  • For supply chain agility, the example (which features a plug for a planning software vendor) of AI / ML, is a double-edged sword. Historically, software has been a great force to rigidify systems, lowering their operating costs, but usually making them less agile too.
  • For sustainability, frankly, this is pure virtue-signal, both from the article itself, and from the respondent of the survey. I am not saying that sustainability isn't a worthy goal, however, very companies are in any position to do much on this front as far as their supply chain is concerned.

Afaik, those types of ships are typically referred to as bulk carriers

A bulk carrier or bulker is a merchant ship specially designed to transport unpackaged bulk cargo — such as grains, coal, ore, steel coils, and cement — in its cargo holds.


The interesting element is the extra option that COSCO gains by being able to leverage one extra type of ship. This method is probably inferior cost-wise to regular containers, but if a bulk carrier is the only ship that happens to be available, then, it becomes very valuable to have the option.

vermorel 8 months | flag | on: How to calculate true demand (2021)

The post points out that competing a "demand" needs to factor-in the delivery date (requested) vs the shipped date (realized). However, I am afraid, this is a very thin contribution.

Demand is an incredibly multi-faceted topic. Demand is never observed. Only sales, or sales intents are observed. The sales are conditioned by many (many) factors that distort the perception of the demand.

First, let's start with the easy ones, the factors that simply censor your perception of the demand:

  • No having the right product to sell. The sales never happen, yet, demand was there.
  • Not having the right price. Idem, demand exists, just not for this price.
  • Not having the right position (bad image, bad description). Visitors miss what they could have wanted.
  • Not having the right delivery promise. Visitors give up if out-of-stock or if delivery date is too far away.

Then, we have all the big factors:

  • Say's law: Supply creates its own demand, demand isn't prexisting, it's engineered as such.
  • Branding: take two physically identically product plus/minus the brand, demand changes entirely.
  • Cannibalizations and substitutions: demand covers a whole spectrum of willingness to buy. Demand cannot be understood at the product level.
  • etc

Looking at the demand through the lenses of time-series analysis is short-sighted.

Ps: thanks a lot for being one of the first SCN contributors!

In 2011 Lidl made the decision to replace its homegrown legacy system “Wawi” with a new solution based on “SAP for Retail, powered by HANA”. [..] Key figure analyzes and forecasts should be available in real time. In addition, Lidl hoped for more efficient processes and easier handling of master data for the more than 10,000 stores and over 140 logistics centers.
The problems arose when Lidl discovered that the SAP system based it's inventory on retail prices, where Lidl was used to do that based on purchase prices. Lidl refused to change both her mindset and processes and decided to customise the software. That was the beginning of the end.

Disclaimer: Lokad competes with SAP on the inventory optimization front.

My take is that the SAP tech suffered from two non-recoverable design issues.

First, HANA has excessive needs of computer resources, especially memory. This is usually the case with in-memory designs, but HANA seems to be one of the worst offenders (see [1]). This adds an enormous amount of mundane friction. At the scale of Lidl, this sort of friction becomes very unforgiving - every minor glitches turning into many-hours (sometime multi-days) fixes.

Second, when operating at the supply chain analytical layer, complete customization is a necessity. There is no such thing as "standard" decision taking algorithm to drive a replenishment system moving billions of Euros worth of good per year. This insights goes very much against most of design choices which have been made in SAP. Customization shouldn't be the enemy.


This spreadsheet contains a prioritized inventory replenishment logic based on a probabilistic demand forecast. It illustrates how SKUs compete for the same budget when it comes to the improvement of the service levels while keeping the amount of inventory under control. A lot of in-sheet explanations are provided so that the logic can be understood by practitioners.

vermorel 8 months | flag | on: The beer game

This is a nice readily accessible implementation, no sign-up, no login, create a new game and play. For those who are not familiar with the beer game, it's 4 stage supply chain game with 4 roles: manufacturer, distributor, supplier, retailer. Each player fills a role, and tries to keep the right amount of goods flowing around. It's a nice - and somewhat brutal - way to experience a fair dose of bullwhip. If you don't have 3 friends readily available, the computer will play the other 3 roles.

Ps: I never got the chance to experience this game at university. If some people did, I would love to hear about their experience - as students - of their first 'Beer game'.

For those wondering about this VizPick technology, there is a short video demo from two years ago at

The UX isn't perfectly smooth. You can feel the latency of the recognition software. Also, the operator has to move relatively slowly to give a chance to the acquired digital image to stabilize. However, it still beats the human perception by a sizeable margin.

vermorel 8 months | flag | on: Launching Supply Chain News

Thanks and welcome! Don't hesitate to submit a link of your own, and/or to post a question. You will benefit from an extra level of care being on of the first non-Lokad contributors. :-)

Unfortunately, S&OP processes - at the very least those I had the chance to observe in my career - had already devolved into tedious iterated sandbagging exercises, exclusively moving targets up or down without - ever - touching any actual decision. Yet, the insight remains correct, without putting the decision front and center, it devolves into idle speculations about the future.

vermorel 8 months | flag | on: Launching Supply Chain News

Side story: this discussion board has been a long-time project of mine. For years I have been looking for a minimalistic discussion board, but all I could find was bloated pieces of software that did 10x what I wanted, and were missing the few things I cared about - like mathematical notations, (hey, have a look at my EOQ, $Q=\sqrt{\frac{2c_l\cdot k}{c_s}}$). More recently, the big platforms started doubling down on both fact checking - as if such a thing was possible when operating platforms that discuss everything and the rest - and monetization. Both being quite toxic to healthy open discussions. This renewed my sense of urgency for this project.

Yet, I believe that an online community does require neither a big platform to operate, not a heavy handed moderation policy. As long you don't have to deal with millions of users, a few careful design decisions can alleviate the bulk of the usual problems that plague online communities (spamming, trolling, brigading).

About 10 days ago, I started actually working on the Supply Chain News project. For the tech-inclined, I have implemented this webapp in C# / .NET 6 / ASP.NET with minimal amount of JS. The persistence is performed via Lokad.AzureEventStream, an open source project of Lokad. I might open source this very forum at some point, once the webapp is a little more battle tested.

A system is a whole that contains two or more parts, each of which can affect the properties or behavior of the whole [..]. The second requirement of the parts of a system is that none of them has an independent effect on the whole. How any part affects the whole depends on what other parts are doing. [..] A system is a whole that cannot be divided into independent parts.

Supply chain is a system, in the purest sense as defined by Russell Ackoff. Approaching supply chains through systems thinking is critical to not entirely miss the point. Most practitioners do it instinctively. However, most academic treatments of the supply chain entirely miss the point.

There are three different ways of treating a problem. One is absolution. That's the way we trust most problems. You ignore it and you hope it'll go away or solve itself. [..] Problem resolution is a way of treating a problem where you dip into the past and say what have we done in the past that suggest we can do in the present that would be good enough. [..] There is something better to do a problem than solving it and it's dissolving it [..] by redesigning the system that has it so that the problem no longer exits.

Dissolving problems is incredibly powerful. A decade ago, Lokad (mostly) dissolved the forecasting accuracy problem through probabilistic forecasting. Instead of struggling with inaccurate forecasts we embraced the irreducible uncertainty of the future, hence mostly dissolving the accuracy problem (not entirely, but to a large extend).

late 15c., "any small charge over freight cost, payable by owners of goods to the master of a ship for his care of the goods," also "financial loss incurred through damage to goods in transit," from French avarie "damage to ship," and Italian avaria.

Supply chain has been shaping the terminology of mathematics.

The M5 forecasting competition was notable on several fronts:

  • It uses a sizeable real-world store-level sales dataset provided by Walmart. With 40k SKUs, it is - to date - the largest publicly assessible dataset for retail sales data.
  • It features a probabilistic perspective letting the participants compete over a series quantile estimates. To date, it's the only forecasting competition featuring a non-average non-median scoring criterion.
  • With 1,137 participants, it was very sizeable event. To date, I don't know any other forecasting competition that did even approach this level of participation.

The findings are not overly surprising: gradient boosted trees and deep learning models - which dominate the vast majority of the Kaggle competitions - end-up dominating the M5 as well.

Caveat emptor, those models are quite dramatically greedy in terms of computing resources. For a retail network of the scale of Walmart, I would not recommend those classes of machine learning models.

vermorel 8 months | flag | on: Supply Chain Rhapsody [video] (2019)

This video has ~47k at the time of the comment which is a shame, because this video is pure gold.

Brands have long known the power of the Made In Your Country sticker. It seems that the practice is over 4000 years old

The Librem example is striking because they literally quantify the extra willingness to pay of their clients to benefit from the right country of origin.

For another discussion about the bullwhip effect, check this discussion with Prof. Stephen Disney (University of Exeter):

More generally, I am trying to consolidate a whole series of lectures about SCM that you can see at:

Shaun Snapp (principal at Brightwork Research) delivers an analysis that matches my own empirical observations about HANA, an analytics platform sold by SAP. The in-memory paradigm is expensive, pretty-much by design, due to both CAPEX and OPEX costs associated with the ownership of terabytes of DRAM, the class of devices that hold the memory in modern servers. Among the in-memory options for enterprise analytics, HANA appears to be one of the worst offenders of the market in terms of costs. Unfortunately, it does not appear to deliver features that can't be replicated in much cheaper systems. Nowadays, PostgreSQL, with a proper columnar setup, is a superior alternative in every dimension that I can think of.

Ryan Petersen is the CEO of Flexport, a startup that raised $2.2B. Flexport is a supply chain platform to track and manage orders.

Indeed, barcodes predate QR-codes, but QR-codes aren't necessarily superior. Information density comes as a tradeoff when it comes to the scanning apparatus and the need for ambient lighting. If you want to convey more information, then RFID is more appropriate than (hypothetic) higher dimensional barcodes. Alternatively, a QR-code is enough to encode a URL, and all the relevant information can be pulled from the internet instead of trying to cram the data into the label itself.

Close to three-quarters of supply-chain functions rely on the simplest method: spreadsheets. In addition, more than half use SAP Advanced Planning and Optimization (APO), a popular but antiquated supply-chain-planning application that SAP introduced in 1998 and will stop supporting in 2027. The portion of APO users in certain industries is even higher—75 to 80 percent of all the automotive, retail, and chemical companies we polled.

This 3/4 estimate for the supply chain functions that rely only on spreadsheets feels right. This is also matching my experience. Furthermore, even when some kind of planning tool is present, the tool almost invariably relies on the alerts & exceptions design antipattern which ensures a very low productivity for every employee that touch the piece of software.

However, I disagree with process suggested for the vendor selection. More specifically, the section that outlines the suggested process for the client company:

A list of business requirements.
Clear evaluation criteria.
Two or three “must have” use cases.

Companies invariably do an exceedingly poor job at any of those three tasks which are exceedingly technology dependent. This process guarantees a bureaucratic selection which favors whoever can tick the most boxes in the RFP document. Bloatware is the enemy of good software.

There is a much simpler, faster and more importantly accurate way to proceed through a vendor-on-vendor assessment:

It is an object of the invention to provide automatic apparatus for classifying things according to photo-response to lines and/or colors which constitute classification instructions and which have been attached to, imprinted upon or caused to represent the things being classified.

Much of what makes the modern supply chain only become possible thanks to the widespread usage of the barcode technology. It's fascinating to see that the barcode predates mainframe computers which only started to get traction in the late 1950s.

Paradoxically, data is the most under-valued and de-glamorised aspect of AI.

Lack of focus on the data plumbing spells the doom of most supply chain initiatives. While this article wasn't written with supply chain use-cases in mind, it's clearly relevant to the supply chain field. Data plumbing being "glamorous" means that it's difficult to gather resources for stuff that don't really have any kind of visible payback. Yet, data engineering is a highly capitalistic undertaking.

Ha ha. It's the pending $1 billion question that haven't cracked yet at Lokad.

Unfortunately, this article gives away very little about what Google may or may not do for supply chains. This article is written like a marketing piece. Nowadays, pretty much every single software company is using at least two cloud computing platforms to some extent. Thus, it's should be a surprise if a Software Company X that happens to do produce supply chain software runs on Cloud Platform Y. Yet, it this doesn't say why this cloud platform is better suited than its competitors.

The article puts forward Vertex AI, a recent ML offering of Google. However, as per the documentation of Google, it's state Pre-trained APIs for vision, video, natural language, and more which gives strong-vibes of being absolutely not the right quite of ML for supply chain. Furthermore, the AutoML (featured by Vertex AI) is also the sort of technology I would strongly recommend not using for supply chain purposes. It adds massive friction (compute costs, development times) for no clear upside in production.


Even with the behemoth dominating the e-commerce landscape, there’s room for smaller, scrappier rivals, Giovannelli says. In fact, many independent service providers are under contract to Amazon and other e-tailers to fill out the growing need for delivery vehicles.

In short, Amazon supply chain is a massive success, and just like the iPhone of Apple, it proves that there is a vast market waiting for alternatives. When considering large markets, even dominant players like Apple struggle to reach 25% market share. This is gives a lot of room for other actors. This is what those private equity investors are looking for.

Within the Lokad TV channel, this episode about DDMRP is probably the one, so far, that generated the most polarized feedback. On one hand, we got a lot of support. On the other hand, we got heavy criticized by the DDMRP evangelists. The most frustrating part of me is that the critics have been, so far, have only been shallow dismissals, or authority arguments.

A longer written discussion was produced at:

Year's later, DDMRP community has still not addressed my top three objections:

  • Incorrect baseline: half-backed MRPs can't be a baseline for DDMRP.
  • Limited formalism: BOMs are literally applied graph theory, which DDRMP ignores.
  • Real-world complexity dismissal: economics are absent from DDMRP.

It will be on September 14th at 15h00 (CET).

Watch the live at:

vermorel 8 months | flag | on: The last days of Target (2016)

Most supply chain initiatives fail, and yet, the vast majority of supply chain case studies speak only of successes. Only the epic-scale failures become visible to outsiders. Even insiders frequently don't realize that most of the past initiatives of their own company have failed. Large companies aren't necessarily very capable when it comes to their institutional memory of past debacles.

The case of Target Canada was discussed in my supply chain lecture: