|
|
|
Posted
over 1 year
ago
by
Joannes Vermorel
Evaluating the quality of a forecasting method can be dramatically complicated. In order to help the community finding out who's delivering the best forecasts out there :-), we have just produced a video concerning accuracy measurements of sales
... [More]
forecasts. Not all metrics are born equal.
Special thanks to Ray Grover for the voice-over. [Less]
|
|
Posted
almost 2 years
ago
by
Joannes Vermorel
Our flagship inventory optimization product, Salescast, has benefited from a major documentation refresh about 3 months ago. Now it's the turn of the user interface (UI) to be extensively redesigned. Here below is a screenshot illustrating the new
... [More]
look & feel (deployed today).
The previous UI was suffering from several problems:
not following UI standards, making it harder for everyone to figure out how Salescast was working. In this version, we have paid a lot more attention to make Salescast not only simpler, but closer to the de facto standards (Amazon, Facebook for example). People should not have to think about UI.
not focusing on changes, complicating the team usage of Salescast. In this version, the most notable UI addition is the Recent Activity listing that tells who has been doing what. Recent activity is a killer feature for teamwork. A lot of teamwork confusion happen job just because Bob did not tell Alice, he had just generated a new report. Now Alice will immediately notice what Bob has done, by simply looking at the recent activity.
confusion between queries and commands, triggering the generation of new reports (and causing extra charges!) while the intent was only to browse existing reports. Now, the commands are put on the right while the queries (read only) are gathered on the left. By establishing this simple distinction, we hope to siginificantly reduce the number of misclicks.
Since it's initial release 15 months ago, Salescast has steadily improved, and this release is certainly not our final word. More good stuff is coming. Stay tuned.
Side note: a new logo for Salescast is also under way :-) [Less]
|
|
Posted
almost 2 years
ago
by
Joannes Vermorel
Bitcoin is a nascent crypto-currency that has attracted a lot of attention lately. For those who've never heard of Bitcoin yet, you can check the good analysis of The Economist. We believe that Bitcoin is a tremendous opportunity to
... [More]
vastly reduce payment frictions for companies operating online such as Lokad.
Thus, in order to facilitate the bootstrap of the emerging Bitcoin economy, we have decided to accept Bitcoins as payment method.
Moreover, for the time being, Bitcoin payments come with a 10% discount as a favor made to early adopters. Contact us for up-to-date conversion rates.
We anticipate that the Bitcoin adoption will be faster among eCommerce compared to classical retail. Through Salescast, online merchants can forecast their sales and optimize their inventory levels based on those forecasts. We hope to make Bitcoin-powered eShops even more productive through advance inventory optimization. [Less]
|
|
Posted
almost 2 years
ago
by
Joannes Vermorel
A couple of weeks ago, we disclosed our plans concerning Shelfcheck, our future on-the-shelf availability optimizer targeting (physical) retailers. Since that time, we have been steadily moving forward, crushing a lot of point-of-sale
... [More]
data.
Lokad isn't the only one company out there trying to tackle the OOS (out-of-shelf) issue, but there is very little literature about how to assess the respective merits of two OOS detectors. In this post, we review two fundamental metrics that define how good is a system at detecting OOS.
Intuitively, an indirect OOS detector (such as Shelfcheck) relies on the divergence between observed sales and the expected sales. Since random (aka unpredictable) fluctuation of the market can always happen, this approach, by construction, cannot be a perfect system (1), it's a tradeoff between sensibility and precision.
(1) Not being perfect does not imply being worthless.
The sensibility represents the percentage of OOS (aka the positives to be detected) that are captured by the system. This concept is already widely used in diverse areas ranging from medical diagnostics to airline security. The higher the sensibility the better the coverage of the system.
Yet, by increasing the sensibility, one also decreases the specificity of the system, that is to say, one decreases the percentage of non-OOS flagged as such (aka the negatives that should not be detected). In practice, it means that by pouring more and more alerts, the OOS detector gives more and more false alerts, wasting the time of the store teams looking for non-issues.
Although, specificity is not a very practical criteria in the case of retail. Indeed, OOS products only represent a small fraction of the non-OOS products. Several studies quote 8% OOS as being a relatively stable worldwide average. Hence, the specificity is typically very high, above 90%, even if the OOS detector happens to be producing pure random guesses. Hence, those high specificity percentages are somewhat misleading as they only reflect the imbalance that exists between OOS and non-OOS in the first place.
At Lokad, we prefer the precision that represents the percentage of accurately identified OOS within all alerts produced by the system. The precision directly translates into the amount of efforts that will not be wasted by the store staff checking for non-existent problems. For example, if the precision is at 50%, then one alert out of two is a false-alert.
Neither 100% sensibility nor 100% precision is possible, or rather if you have 100% sensibility then you have 0% precision (all products being classified as OOS all the time). The other way around, 100% precision indicates that you have 0% sensibility (no alert gets ever produced). The tradeoff sensibility vs precision cannot be escaped: if you want to detect anything, you need to accept that a some what you detect is incorrect.
In order to compare two OOS detectors, one needs to access their respective sensibility and precision. Then, in order to improve both the sensibility and precision, it remains possible to leverage a superior forecasting technology, as better forecasts will improve both the sensibility and precision.
Although, this raises another concern, how do you compare the following:
a detector A with 70% sensibility and 60% precision;
a detector B with 60% sensibility and 70% precision.
It turns out that this question cannot be addressed in a purely statistical manner: one needs to model the economic costs and benefits in order to assess the optimal choice.
Stay tuned for more. [Less]
|
|
Posted
almost 2 years
ago
by
Matthias Steinberg
Our growing development team in Russia has a new home: This week, Lokad’s new development center opened its doors in Ufa. The office opening is an important step in consolidating our development capabilities and expertise in Russia and
... [More]
laying the foundations for further expansion. The office will be lead by Rinat Abdullin, Lokad’s Technology Leader.
Ufa is the capital of the Republic of Bashkortostan, Russia and situated near Eastern Europe's land boundary with Asia. Approximately 1 million people are currently enjoying average temperatures of up to 26C and endure up to -40C in Winter. Ufa's industry is dominated by oil refining and manufacturing.
The choice of location might puzzle, were it not for the Bashkir State University, which is among the top ten classical universities in Russia. It is especially strong in applied mathematics and information technologies. Many prominent applied mathematicians and physicists were among the faculty at different times, and the Department of Mathematics and the Ufa Institute of Mathematics including its Computing Center are among the best Russian schools in Applied Mathematics.
Our technology combines the triple mastery of statistics, enterprise software engineering and cloud computing in its most advanced forms. The only way to tackle this complexity is by working with the best people in its field worldwide, irrespective of where we find them. Ambitious new development initiatives such as Shelfcheck, an on-shelf availability monitoring tool for retail, require further investments in highly talented people. With Paris (France) and Ufa we now have two development locations that draw from extremely strong talent pools.
We are particularly pleased to see a red sofa appearing in the communal areas of the Ufa location. At the risk of giving away company secrets – a similar piece of furniture has been the breeding ground for some of the best ideas in Paris...
[Less]
|
|
Posted
almost 2 years
ago
by
Joannes Vermorel
Last Wednesday, at the Strategies Logistique Event in Paris, we announced a new upcoming product named Shelfcheck. This product targets retailers and it will help them to improve on-shelf availability, a major issue for nearly all retail
... [More]
segments.
In short, through an advance demand forecasting technology such as the one of Lokad, it becomes possible to accurately detect divergence between real-time sales and anticipated demand. If the observed sales for a given product drop to a level that is very improbable considering anticipated demand, then an alert can be issued to store staff for early corrective actions.
On-shelf availability has been challenging the software industry for decades, yet, as far we can observe, there is no solution even close of being satisfying available on the market at present day. For us, it represents a tough challenge that we are willing to tackle. We believe on-shelf availability is the sort of problem that is basically near-impossible to solve without cloud computing; at least near-impossible within reasonable costs for the retailer. Shelfcheck will be deployed on Windows Azure, a cloud computing platform that proves extremely satisfying for retail, as illustrated by the feedback we routinely get for Salescast.
A retail pain in the neck
Have you ever experienced frustration in a supermarket when facing a shelf where the product you were looking for was missing? Unless, you've been living under a rock, we seriously bet you face this situation more than once.
Recent studies (*) have shown that, on average, about 10% of the products offered in store are unavailable on average. Worse, the situation seems to have slightly degraded over the last couple of years.
(*) See materials published on ECR France.
In practice, there are many factors that cause on-shelf unavailability:
Product is not at the right place and customers can't find it.
Product has been stolen and incorrect electronic inventory level prevents reordering.
Packaging is damaged and customers put in back after having a close look.
...
Whenever a product is missing from a shelf, sales are lost, as studies have shown that clients go for a direct ersatz only 1/3 of the time. Then it generates client frustration too which turns into loss of loyalty. Missing products are putting an incentive on your clients to check if competitors are better.
With about 10% on-shelf unavailability, a back-of-the-envelope calculation indicates the losses for the retail industry amount for a rough 100 billion USD per year world-wide. Disclaimer: that's only an order of magnitude, not a precise estimate. Then, this estimate does not factor industry-wide cannibalizations, aka lost sales aren't always lost for everyone.
You can't improve what don't measure
On-shelf availability is especially painful because detecting the occurrence of the problem is so hard in the first place:
Direct shelf control is extremely labor intensive.
RFID remains too expensive for most retail segments.
Rule-based alerts are too inaccurate to be of practical use.
Thus, the primary goal of Shelfcheck is to deliver a technology that let retailers detect out-of-shelf (OOS) issues early on. Shelfcheck is based on an indirect measurement method: instead of trying to assess the physical state of the shelf itself, it looks at the consequences of an OOS within real-time sales. If sales for a given product drop to a level that is considered as extremely improbable, then the product is very likely to suffer an OOS issue, and an alert is issued.
By offering a reliable OOS metering system, Shelfcheck will help retailers to improve their on-shelf availability levels, a problem that proved to be extremely elusive to quantitative methods so far.
Store staff frustration vs. client frustration
The core technological challenge behind Shelfcheck is the quality of OOS alerts. Indeed, it's relatively easy to design a software that will keep pouring truckload of OOS alerts, but the time of the store staff is precious (expensive too), and they simply can't waste their energy chasing false-positive alerts, that is to say "phantom problems" advertized by the software, but having no real counterparts within the store.
Delivering accurate OOS, finely prioritized and mindful of the store geography (*) is the number one goal for Shelfcheck. Considering the amount of data involved when dealing with transaction data at the point of sale level, we believe that cloud computing is an obvious fit for the job. Fortunately, the Lokad team happens to somewhat experienced in this area.
(*) Store employees certainly don't want ending-up running to the other side of the hypermarket in order to check for the next OOS problem.
Product vision
The retail software industry is crippled by consultingware where multi-millions dollars solutions are sold and do not live up to expectations. We, at Lokad, do not share this vision. Shelfcheck will be following the vision behind Salescast, our safety stock optimizer.
Shelfcheck will be:
Plug & Play, with simple documented ways of feeding sales data into Shelfcheck.
Dead simple, no training required as Lokad manages all the OOS detection logic.
Robotized, no human intervention required to keep the solution up and running.
SaaS & cloud hosted, fitting any retailers from the family shop up to the largest retail networks.
The pricing will come as a monthly subscription. It will be strictly on demand, metered by the amount of data to be processed. We haven't taken any final decision on that matter, but we are shooting for something in the range of $100 per month per store. Cost will probably be lower for minimarkets and higher for hypermarkets. In any case, our goal is to make Shelfcheck vastly affordable.
Feature-wise, Shelfcheck is pre-alpha stage, hence, the actual feature set of the v1.0 is still heavily subject to change. Yet, here is the overview:
Real time OOS alerts available through web and mobile access.
Real time prioritization based on confidence in the alerts and financial impact of the OOS issues.
OOS dashboard feeding the management with key on-shelf performance indicators.
1 year free usage for early adopters
We are extremely excited by the sheer potential of this new technology. We are looking for volunteers to beta-test Shelfcheck. Lokad will offer:
Until Shelfcheck is released, early adopters will be provided with unlimited free access.
Upon release, early adopters will get 1 year of further free usage, within a limit of 10 points of sale.
In exchange, we will kindly ask for feedback, first about the best way for Lokad to acquire your sales data, and second about the usage of Shelfcheck itself.
Naturally, this feedback will drive our development efforts, bringing Shelfcheck closer to your specific needs. Want to grab the opportunity? Just mail us at contact@lokad.com. [Less]
|
|
Posted
almost 2 years
ago
by
Joannes Vermorel
Many people at Lokad are bloggers. We try to keep the official blog focused on our core forecasting business, but here is a sample of posts made by team members during the last week. 3 Low-Competition Niches In Retail
... [More]
Software by Joannes Vermorel (@vermorel), Founder at Lokad. Software developers seem to be herd animals. They like to stay very close to each other. As a result, the marketplace ends up riddled with hundreds of ToDo lists while other segments are deserted, despite high financial stakes. During my routine browsing of software business forums, I have noticed that the most common answer to "Why the heck are you producing yet another ToDo list?" is the desperately annoying "Because I can’t find a better idea." Read more.
A simple, non-technical definition of cloud computing by Matthias Steinberg (@mfsteinberg), CEO at Lokad. Last year, I found myself researching the market for investment opportunities in ‘cloud computing companies’, driven by the insight that this was a rapidly growing market. Yet, it felt a bit like hunting the Yeti as I was having a hard time understanding what exactly cloud computing is, and what it is not. Realizing that I shared this confusion with a lot of my peers, I thought it is worth sharing some insights I gained in the last month. Read more.
Lokad.CQRS v2.0 Framework and Docs for Windows Azure by Rinat Abdullin (@abdullin), Technology Lead at Lokad.The project was started 1.5 years ago to provide simple light-weight service bus for Windows Azure Cloud. It did the job well and eventually got accepted into more projects inside Lokad and outside as well. This gave us more feedback from the production usages in cloud, along with new development experience and CQRS ideas. Second version builds upon that and also includes first decent documentation. Read more. [Less]
|
|
Posted
almost 2 years
ago
by
Joannes Vermorel
Our clients need better forecasts, but they also need better insights. Salescast, our webapp dedicated to retail, wholesale and manufacturing was having about 200 words of documentation, which, by any standard was thin. Hence, over the
... [More]
last couple of weeks, we gathered materials, and this morning, we released about 7000 words of documentation concerning Salescast ins and outs.
First, we clarify the scope of Salescast, with special focuses on large retail networks, eCommerce and manufacturers. In short, if your company has inventory, then Salescast do apply to your case.
Furthermore, we details pros and cons of statistics. There are limits in what can be achieved through statistics; and Lokad does not come with divination capabilities.
As a rather touchy subject, we also position Salescast against our competitors. Naturally, we have a rather biased viewpoint here. So in the end, it comes down to benchmark us and see for yourself.
Also, Salescast isn't even remotely intended as a silver-bullet for supply chain. Lokad is a rather social software company in the sense it plays well with buddies, aka other complementary apps.
Nonetheless, Salescast does have some nice features on its own. It delivers Excel reports with both forecasts and key inventory optimization metrics (but you probably know that already). Just in case, here is a sample Excel report.
At this point, people typically ask How does your forecasting engine works? and How much does it cost? We already had two pages, namely Technology and Pricing, addressing those two questions, but we have tried to adopt a more practical angle here.
Once all those items are cleared, it's time to get started with Lokad. From there, you should quickly end-up with your first forecast report delivered. Expect the unexpected, forecasting is a counter-intuitive science. [Less]
|
|
Posted
about 2 years
ago
by
Joannes Vermorel
Europe’s dedicated magazine for the supermarket sector ESM is featuring Lokad this month in a two page article titled Embracing the Cloud. The publication gives a great overview of Lokad to retailers and details why the cloud is such
... [More]
a game changer for retail. ESM had taken notice of Lokad’s presentation at the EuroShop 2011 in Düsseldorf, which particularly impressed the Editor Kevin Kelly.
Also, we agreed to offer ESM’s readers a free proof of concept to benchmark the retailer’s current forecasting accuracy compared to the one delivered by Lokad. Consider a 3 weeks net execution time to get hard facts on your forecasting practice.
In this issue, ESM investigates the highly competitive European grocery market, including the growing prominence of private labels, covers areas of interest to both buyers and other senior management working in the retail and manufacturing sectors, such as supply chain and logistics management, technology (such as EPoS), packaging and design and environmental best practices. The magazine appears bimonthly. [Less]
|
|
Posted
about 2 years
ago
by
Joannes Vermorel
Joannes Vermorel, founder of Lokad, discusses with Bruno Aziza, Director, Worldwide Strategy, Analytics and Business Intelligence at Microsoft, how companies are using the cloud to turn hard data into sales forecasts that enable them to optimize inventory and staffing. The interview was shot in New York during NRF11.
|
Copyright
©
2013
Black Duck Software, Inc.
and its contributors, Some Rights Reserved. Unless otherwise marked, this work is licensed under a
Creative Commons Attribution 3.0 Unported License
. Ohloh
®
and the Ohloh logo are trademarks of
Black Duck Software, Inc.
in the United States and/or other jurisdictions. All other trademarks are the property of their respective holders.