Video

According to the DDMRP book (2019, Ptak and Smith), this method governs the inventory buffers mostly through a direct application of the ADU (average daily usage). The book remains fuzzy on how this ADU is computed exactly, but simple averages are somewhat implied through most of the examples given in the book. Hope it helps. Cheers, Joannes

I am currently working on such a book - precisely because I am quite dissatisfied with the present state of affairs of the supply chain literature. It's going to be somewhat lengthy book.. Stay tuned! Cheers, Joannes

In order to mechanize the decision-making processes, there is no alternative, but to "map each one piece by piece into the algorithm" as you very correctly suggest. This is one of the core responsibilities of the Supply Chain Scientists at Lokad. Cheers, Joannes

The issue of not being able to access the adequacy of a decision until long *after* the decision was made is equally present for people. Having a human making the decision does change anything with regards to this challenge. Humans have no special powers in this area. If at the time the decision is generated (by an algorithm), a human can object to the long-term viability of the decision, and if this objection is well-reasoned; then the algorithm must be modified to immediately take this into account. Automation doesn't preclude keeping human intelligence around to adjust or improve the automation itself. Furthermore , if the decision is automated, it is possible *after the fact* to modify the logic so that the same mistake isn't made again. This property is in sharp contrast with employees who may or may not comply, who may or may not learn from the mistake, or who may arrive fresh and ignorant due to turnover. Joannes

Becoming proficient in SQL and Python is key. Those are foundational skills that will only become more important in the next decade. Fancy data science is the cherry on the cake, but it won't hurt either. A traditional 'masters' feels very expensive time-wise to gain those skills, but assuming you can complete your online master without quitting your current job, and assuming the price is reasonable, yes, it will certainly put you in the bracket of the more desirable sort of employees. Hope it helps! Cheers, Joannes

Thank you for the kind word, it's very appreciated. Yes, Lokad is growing very nicely and hiring accordingly. The open positions are listed at www.lokad.com/about-us/#positions Also, you can check out the jobs that we post on LinkedIn. Best regards, Joannes

Glad you enjoyed it! Joannes

Absolutely. Yet, not all numerical recipes are equal in their capacity to generate results that make sense - even for the data scientists who understand the algorithms. This is why we have a whole process referred to as 'white boxing' at Lokad to address this. Best regards, Joannes

Python is more versatile option than R, and over the last decade, it has grown into a "classic" general purpose programming language, much like Java or C#. I would recommend Python, but more importantly, I would recommend learning about software and software engineering in general. Mastering the programming syntax is one of the easiest parts of software. Best regards, Joannes

Hi! It simply means a line/border separating two (or more) things. It is the same term used to describe borders ("frontiers") that separate countries - e.g., the Pyrenees form a natural frontier between France and Spain. In this context, Harvard Business School suggests there is a digital frontier between the things gen-AI (ChatGPT-4) can do well and the things it cannot do well. We disagree. See this essay for a greater explanation of our position: www.lokad.com/blog/2024/4/8/a-nuanced-perspective-on-jagged-technological-frontier/

It is certainly unfair to use an LLM for complex quantitative tasks and then say "hey, look at how badly it did!" In case you are interested, we expanded our critique of the paper here: www.lokad.com/blog/2024/4/8/a-nuanced-perspective-on-jagged-technological-frontier/

Thanks for the kind word! We are going to publish soon an upcoming debate about S&OP. Tons of further materials in this long interview. Stay tuned! Best regards, Joannes

Thank you. Best, Joannes

Working on it! This is exactly the sort of question that I want the Lokad chatbot to cover. See lokad.com/chat It's not there yet, but I have started to compile a list of book reviews to be (later) fed to this chatbot. Cheers, Joannes

The job market will sort it out, it always does - unless misguided state interventions prevent it do so. New and better jobs will emerge, even if it's unclear what those jobs will be exactly. 150 years ago, farming was +80% of the labor workforce, in the US, in France and pretty much everywhere. Now, it's about 1.5% of the workforce. 90% of the back-office tasks of the 1970s have already disappeared. Remember the time when most junior white collars would spend a few months in the mailroom? My parents do, but those times are gone. The media relentlessly paints automation as the villain, but visit any country that does not enjoy massive modern automation, and it's dire poverty for everyone but the 0.01% elite. My 2cts, Cheers, Joannes

@Lokad Thank you for the answer to my badly worded question. The part I forgot about was that for those with a high school education or lower MIT, believes since 1980 70-50% of income inequality is a result of automation. They think the AI revolution will only make this worse. America has one of the worst education systems, along with the vast majority of immigrants only having a high school education or lower. How can a society function when large chucks of your population only have rudimentary education when all the new jobs require skilled labor?

Hi Kurtney, Joannes addresses this question here: czcams.com/users/live4xeV0YVRK68?si=Ug9E8lo5FmlR7dLN&t=3995. Here are the lectures he talked about: www.lokad.com/tv/tag/supply-chain-lectures/. Generally speaking, an engineering degree - solid knowledge of math, statistics, computer science combined with programming skills are and will be crucial.

​@Lokad, I appreciate the information!

Thanks for the kind word! The 'action reward' can end-up favoring either of the two options depending on the probability distribution of the demand. Indeed, if the demand is very dispersed, then, committing to Option II (bigger order) is very risky, as there is a much bigger risk of overstock; hence Option I will be favored if the inventory risk outweights the transport overhead. On the contrary, if the demand is very steady, then, the transport overhead will dominate, and assuming that the stock doesn't rapidly expire either, Option II will be favored. Hope it helps, Joannes

Thank you! Joannes

Your reasoning looks correct. In the example given, we have 3 SKUs, 2 categories and 7 days a week. Thus, 'SKUs.Level' is 3 parameter values; and CD.DoW is 2 * 7 = 14 parameter values. Cheers, Joannes

Indeed, just trying to keep the discussion vaguely relevant to supply chain challenges :-) Cheers, Joannes

- What are these typical operation research topics that I'm saying don't work? - 11:55 - First Time series in demand forecasting - Doesn't work well for unusual demands - For example, where you have consumers who buy switches one at a time and construction companies who buy 500 at a time. - The order for 500 is announced well in advance, while the one offs are immediate, yet a time series will not differentiate between these cases and squash the demand together - For substitutions in fashion - if the wrong size is there - can't sell it, but if its a slightly different color, the customer wil likely still take it - Diapers and market basket effects - Diapers are expensive and have high brand loyalty on average - However it's not the loss of the diaper sale that is the most impactful - it's the fact that parents will then not buy all of their other groceries at the hypermarket if the diapers aren't there. - Time series also hides the fact that the future is blurry and in which direction - Deterministic forecasting works pretty well with consistent values - But a deterministic forecast of something like a soup in a supermarket with promos and demand swings of >100% it makes no sense to generate a point forecast - 1st order effects can be measured such as impact of promotion, but those indirect 2nd order effects e.g. consumer behaviour changes are hugely critical to take into account - 27:15 - For example a spare parts organization of an aircraft company had a recommendation to purchase a part, the employees said absolutely not! - It seemed a reasonable recommendation to make - however it was a spare part for a 747 - and since the part had a 30 year life, and the 747s are being deprecated within the next 10 years there was no need for it - Another interesting effect in airlines is the one-way standard. - A plane is allowed to have a part matching the old standard, however as soon as a part passing the new standard is placed - you must only use new parts going forward. - This means if you have inventory of old and new parts - each time you replace with a new part- you are modifying the composition of your demand for spare parts across your flotilla - Just because we don't know what to optimize for, doesn't mean we can't find out - 29:17 - It just can't be done in a top down cartesian way in which we split the problem down into constituent pieces and come up with an answer that way - We arrived at the need for supply chain scientists to operate under the idea of Experimental Optimization - To optimize you must create logic to generate a decision - you will then have people who object - Their reasons for objecting are typically correct - Use anecdotes to find the reasons it won't work - Then we will feedback into the dollarized/financialized decision making system to add the constraints and requirements that will meet the edge cases which are critical to that customer - For example with the spare parts problem we had taken into account the lifespan of the part, but not the lifespan of the plane itsself - In our supply chain books we tell you the demand is a Gaussian, lead times are a Gaussian - is there any way to falsify this? no, it's in the abstract, divorced from reality - 31:50 - Our goal is to make a mathematical model , maximized for modeling reality, not necessarily mathematical simplicity - An important part of the process is making sure to present the results to the customer in a specific way - not just "here are your optimal stock levels" but - "where should I put my first Euro of inventory investment?" - 80% customers know what they're doing - so this list of prioritized investments in purchasing, manufacturing, or inventory levels is reasonable - though sometimes they may be missing something obvious - Working with a german MRO company - Retrofit and repairs are 2 different things - Repairs are - engineer says this part needs to be fixed, replace - Retrofits are - the manufacturer has some doubts about a part and requires a push to replace within a month - You can't mix push and pull demands together - they act completely differently - You push a big spike of parts - and now all of your spares for that part are synchronized

Awesome summary! Cheers, Joannes

Astutely observed. Indeed. Cheers, Joannes