A numerical take on DDMRP

DDMRP stands for Demand Driven Material Requirements Planning. In the last few years, the popularity of DDMRP has been growing in certain industries; occupying the niche that lean manufacturing or six sigma used to occupy. Yet, what can really be expected from DDMRP and how much novelty does it bring to the table as far as supply chain optimization is concerned?

In order to address this question, let’s review DDMRP from a numerical perspective, i.e. looking at DDMRP as a set of numerical recipes1 to deliver a measurable performance optimization of a given supply chain. Indeed, as all the benefits put forward by the authors of DDRMRP are all quantified targets (ex: achieve 97-100% on time fill rate performance2), it seems fair to adopt a numerical stance to assess the merits of this approach.

The authors behind DDMRP state that this approach brings four key innovations to supply chain optimization, namely:

  • decoupling the lead times3
  • the net flow equation4
  • the decoupled explosions5
  • the relative priority6

Jumping to conclusions, the careful review of each of those points - done in greater details in the following - indicates that there is very little substance to the bold claims of DDMRP. The numerical recipes proposed by DDMRP would not even have been considered state-of-art by the end of 1950’s as the nascent field of operations research had already uncovered arguably more sophisticated and better numerical optimization strategies at the time.

The improvements claimed to be achieved by DDRMP start with a wrong baseline: MRPs - just like ERP - are typically not delivering any numerical optimization capabilities7. Their underlying relational database systems are simply unsuitable to carrying any sizeable data crunching workload, even when considering modern computing computing hardware. Thus, despite the discourse of many enterprise software vendors - operating in the transactional side of the problem - it is incorrect to take MRPs are a baseline as far as supply chain optimization is concerned.

An algebra for supply chain economics

The first principle of our Quantitative Supply Chain manifesto states that all futures should be considered. Thus, we expanded Envision two years ago to natively work with random variables. This probabilistic algebra is the cornerstone of our way of dealing with uncertain futures.

Then, the second principle states that all feasible decisions should be considered, e.g. quantities to be purchased from suppliers. Yet, while those decisions are not random variables. the quantities associated to those decisions are undecided not uncertain. Our probabilistic algebra was not sufficient by itself to properly reflect those yet-to-be-made decisions.

Economics machine

Thus, last year, we silently and gradually rolled out a complementary algebra: the algebra of zedfuncs. A zedfunc is a datatype in Envision intended to reflect economic rewards or losses associated to quantified decisions. The main trick is that a zedfunc does not compute the outcome for one decision, but for all decisions; e.g. all the rewards from triggering a production for 1 unit up to an infinity 1 of units.

Real-time data exploration with slices

Two months ago, we rolled out a major new feature for Lokad: our first bit of real-time data exploration. This feature is codenamed dashboard slicing, and it took us a complete overhaul of the low-level data processing back-end powering Envision to get it done. With dashboard slices, every dashboard becomes a whole dictionary of dashboard views, which can be explored in real-time with a search bar.

For example, by slicing a dashboard intended as a product inspector, which gathers in one place all the information about a product - including probabilistic demand and lead time forecasts for example - it is now possible to switch in real-time from one product to the next.

Envision dashboard with slices

At present, Lokad supports up to 200,000 slices (aka dashboard views) to be produced for a single dashboard; and those slices can be displayed in real time through the selector, which comes with a real-time search feature in order to facilitate the exploration of the data. Unlike business intelligence (BI) tools, those slices can contain highly complex calculations, not merely slice-and-dice over an OLAP cube.

Search box for slices in Envision dashboard

When it comes to data crunching and reporting there are typically two camps: online processing and batch processing. Online processing takes a feed of data, and it is typically expected that everything displayed by the system is always fresh: the system is not lagging more than a few minutes, sometimes no more than a few seconds behind the reality. OLAP cubes, and most of the tools referred to as business intelligence fall into this category. While real-time 1 analytics are highly desirable, not only from a business perspective (fresh data is better than stall data), but also for an end-user perspective (performance is a feature), they also come with stringent limitations. Simply put, it is exceedingly hard to deliver smart analytics2 in real-time. As a result, all online analytical systems come with severe limitations when it comes to the type of analytics that can be carried by the system.

Lean scalable processing for supply chains

With the advent of cloud computing, a little more than a decade ago, it has become straightforward to acquire computing resources on-demand (storage, compute, network) pretty much at any scale as long as one is willing to pay for it. Yet, while it is straightforward to perform large scale calculations over the cloud computing platform of your choice, it does not imply that it will be worth the cost.

Data mountains

At Lokad, we do not charge our clients per GB of storage or per CPU per hour. Instead, the primary driver for our pricing, when opting for our professional services is the complexity of the supply chain challenge to be addressed in the first place. Naturally, we do factor into our prices the computing resources that we need to serve our clients, but ultimately, every euro that we spend on Microsoft Azure - spending-wise, we did become a “true” enterprise client - is a euro that we cannot spend on R&D or on the Supply Chain Scientist who is taking care of the account.

Crafting homepages

Supply chains are complex and as a result our clients frequently end up with a dozen bespoke dashboards, each dashboard being designed as an entry point to address a key business challenge. As the modelization of the supply chain gets refined over time, the complexity of the Lokad account tends to grow as well, merely reflecting the incremental improvements that have been brought so far.

Recently, we realized that while Lokad is tremendously capable of orchestrating a complex quantitative modelization of a world-spanning supply chain, the user experience could be somewhat overwhelming when logging into an account that contains dozens of advanced dashboards.

Columnar Random Forests

Many supply chain challenges can be framed as either classification or regression problems. For example, forecasting demand can be seen as a regression; while deciding whether aligning a price with the price point of a competitor is acceptable can be seen as a classification.

A random forest is a machine learning technique that can be used to learn patterns from data, typically with the intent of performing either a classification or a regression.

While random forests are no longer state-of-the-art machine learning - deep learning outperforms them in many if not most situations - there are still distinctive practical advantages associated with random forests, which have been nicely summarized by Ahmed El Deeb in The Unreasonable Effectiveness of Random Forests.

Indeed, when Ahmed El Deeb points out that It’s really hard to build a bad Random Forest!, I do concur, and this represents a significant practical advantage. In contrast, deep learning models are, well, finicky to say the least, and a trove of obscure parameters can improve - or degrade - performance in ways that are not always very clear to the data scientist.

Thus, random forests are now built-in within Envision. Bonus: the predictions of random forests are returned as random variables which makes a nice combo for probabilistic approaches of supply chain optimization.

Happy New Year 2019!

2018 has been a fantastic year for Lokad - we achieved more than 50% growth while remaining profitable. For 2019, I am wishing the best to our all clients who trusted us and made this possible.

happy-new-year-2019.jpg

Anecdotally, in 2018 among the employees of Lokad French citizens have become a minority, representing no more than 40% of the workforce. Our customer base was already highly international, as France amounts for less than 20% of our revenue, and now the very composition of the Lokad team is catching up with the diversity of our clients, and the reach of their own supply chains.

Dear Systems integrated

Dear Systems, an increasingly popular cloud-based inventory management software, is now natively supported by Lokad.

Website refresh

Lokad turned 10 years old last spring, and a large redesign of our website was well overdue. Earlier this month, we rolled-out a new version of our website. It’s certainly the most usable and best looking website we have ever had.

One of the specific challenges that Lokad faces is the sheer amount of information that we have to convey. Supply chains are complex, and the Lokad platform reflects this complexity: we strive to make things as simple as possible, but not simpler.

We have put our content-heavy sections under a unified Learn umbrella. The technical documentation of Lokad itself has been moved to docs.lokad.com a separate website.

We remain committed to a high degree of transparency, putting as much information about Quantitative Supply Chain and Lokad’s platform itself online.

If you have any supply chain topics that you would like to be covered in greater depth, don’t hesitate to drop us an email to contact@lokad.com. We can’t promise to address all questions, but most of the time, we do.

The limited applicability of backtesting

Backtesting is a design of experiment where one truncates historical data back to a point in the past, and applies a learning algorithm, or an optimization algorithm, against this truncated dataset in order to assess how well this algorithm would have performed under those historical conditions. The approach is simple and elegant, and thus is frequently quite appealing to supply chain practitioners. However, backtesting is far from being a silver bullet, and when its limitations are misunderstood, focusing on backtesting usually does more harm than good.

Improving a forecasting technology

Since Lokad’s creation , our goal has been to relentlessly improve our forecasting technology in order to deliver superior forms of supply chain optimization. Almost a decade ago, I was already pointing out that being a machine learning company is odd: progress is steady but also non-linear and erratic. Furthermore, most angles that are considered as common sense in other domains are plain misguided as far as machine learning is concerned. Yet, this does not imply that this progress is left to chance: there is a method to it.

Launch of LokadTV

As you may have noticed myself and the team here at Lokad have taken advantage of our new glamorous surroundings to work on a number of YouTube videos over the last couple of weeks. Within the videos we discuss the latest advances in technology and explore how they can bring change to the supply chain industry. This is an industry in which we have developed our understanding of over the last decade and we are eager to share some of the knowledge that we have developed along the way.

With clients all over the world, in practically every industry, we have experienced at first hand the frustration that dealing with archaic technology can bring. We have been fortunate enough to help clients overcome this frustration and reap the benefits of a well managed supply chain. The willingness of our customers to buy into our vision has been a key part in our success. We hope that through the medium of these videos we can help more people understand the potential that quantitative forecasting can bring to their organization and understand our disruptive vision of the supply chains of the future.

Our aim through LokadTV is to bring a bit of clarity to a range of topics which, despite vast amounts of media attention, are still remarkably difficult to interpret. You will notice that the discussions are unedited and filmed in one take. This we hope will give them an air of spontaneity and personability which would be lost by ‘over polishing’ the videos. We hope that you find the videos entertaining and educational, however more than anything we hope that they encourage a little bit of debate. We feel that is only by challenging the status quo that we can make progress in the industry and reach a day where supply chains benefit from the latest technology to become faster, leaner and more reliable.

So make sure you subscribe to our channel to keep up to date with the latest episodes.

Forecasting Accuracy

Forecasting accuracy is a subject that often divides the supply chain industry. Practitioners complain that the accuracy of their forecasts is too low whilst software vendors claim to deliver unrealistically precise forecasts.

Forecasting Accuracy

Artificial Intelligence

Artificial intelligence has become a buzzword in the world of technology over the last year or so. It has made numerous headlines with certain experts claiming that AI will replace half of the world’s jobs by 2050. However supply chains are still in the dark ages, too frequently managed by Excel sheets and in a very human driven way.

Artificial Intelligence

Blockchain and Bitcoins

Bitcoin has captured the imagination of the media and it’s easy to see why. With a mysterious, anonymous inventor, bad guys making fortunes with get-rich-quick frauds and random students becoming overnight millionaires it certainly has all the makings of a box-office hit. What about supply chains?

Blockchain and Bitcoins

Expanding office space at Lokad

Over the last couple of months Lokad has passed a number of important milestones, including the implementation of our deep learning forecasting engine and the publication of a new book. All of these milestones have been made possible by the hard work and commitment of the team here at Lokad, a team which is growing by the minute!

In order to make room for this growth, we are proud to announce that we have a new home, located at 83 - 85 Boulevard Vincent Auriol, 75013 Paris, twice the size of our previous location. The area is incredibly up-and-coming, boasting an impressive collection of street-art, as well as being home to a number of multinationals and the largest start-up campus in the world.

When I started Lokad back in 2008 we were a much smaller team working in a much more modest environment. Back then I would certainly not have anticipated that we would grow to such salubrious surroundings. However, it is my hope that this move reflects our ambitions for the future whilst being a comfortable new home for the diverse and industrious team we have built around us.

Office Move Kitchen.png

Office Move Lounge.png

Gold sponsor ACM programming contest

The future of supply chains depends on critical innovation such as deep learning or Bitcoin, the only blockchain that appears to have at least a plausible chance of delivering the massive on-chain scalability that supply chains require. Young talents capable of delivering tomorrow’s innovation should be attracted and nurtured. Thus, Lokad is proud to announce that - thanks to our sponsors CoinGeek and nChain - we have become a Gold Sponsor of the ACM programming context for Southwestern Europe.

youtube video

Programming contests are tough on students. It takes a lot of courage to participate, and naturally a huge amount of talent to have any chance of making it to the top ranks. Yet, it’s also a great opportunity to take part in a high-spirited event, intended to raise the bar of computer science skills of a whole generation.

SWERC participants need to demonstrate superior abilities in solving tough algorithmic problems, which are of primary relevance for supply chains. Indeed, crafting flexible, scalable, expressive algorithms are of primary importance in order to get more accurate demand forecasts and a better resolution for non-linear optimization problems.

Join us at SWERC 2018 and be part of the future of supply chains!

Beyond in-memory databases

Most IT buzzwords age poorly, and for a good reason: most tech that used to have a competitive advantage gets superseded by superior alternatives within a decade or less. Thus, if a software vendor keeps pressing a buzzword past its expiration date (1) then the simplest explanation is that its R&D team has not even realized that the world has moved on. Anecdotally, multiple venture capitalists have also told me that there were weary of investing in any software company that was more than a few years old, because most companies never manage to decouple their own tech from the tech landscape that defined them when they started.

Book: The Quantitative Supply Chain

My latest book, The Quantitative Supply Chain is out! This book presents the Lokad way of envisioning supply chains, which is best summarized through our supply chain manifesto. Your supply chain deserves what machine learning and big data have to offer.

The book can be acquired online.

Lokad will also be offering 100 copies for free to supply chain practitioners. Just drop an email to contact@lokad.com titled Free QSC book from your professional address. The free copies will be served on a FIFO basis, which we feel is the proper way to proceed with a supply chain audience.

From Crps to Cross Entropy

Our deep learning technology is an important milestone for both us and our clients. Some of the changes associated with deep learning are obvious and tangible, even for the non-expert. For example, the Lokad offices are now littered with Nvidia boxes associated to relatively high-end gaming products. When I started Lokad back in 2008, I would certainly not have anticipated that we would have so much high-end gaming hardware involved in the resolution of supply chain challenges.

Deep Learning as 5th gen forecasting engine

As part of our core commitment to deliver the most accurate forecasts that technology can produce, we are proud to announce that our 5th generation of forecasting engine is now live at Lokad. This engine is bringing the largest accuracy improvement that we have ever managed to achieve in a single release. The engine’s design relies on a relatively recent flavor of machine learning named deep learning. For supply chains, large forecasting accuracy improvements can translate to equally large returns, serving more clients, serving them faster, while facing less inventory risks.

MRO Europe in London, join us!

The Lokad team is at MRO Europe 2017 in London this week. Join us at our booth!

The age of online supply chains

We are proud to announce that Lokad now has a native integration for Piwik, an open source web tracking software. In short, Piwik is just like Google Analytics, except that it gives your company full control over your own web traffic data. In particular, it makes sense not to trust the same company with both your SEM (search engine marketing) spendings and your web conversion metrics: Piwik gives you precisely that.