Forecasting 3.0 with Quantile Grids

Delivering better forecasts has always been the core focus for Lokad. Today, we are unveiling the third generation of our forecasting technology based on quantile grids. In layman’s terms, quantile grids demonstrate an unprecedented level of performance which means that your company can service more clients, more reliably, and with less inventory. Unlike all the existing forecasting methods available on the market, quantile grids do not provide one demand forecast per product, but provide the entire probability distribution for (nearly) all possible futures.

Wanted: competitive price monitoring partner

We are seeking an awesome competitive price monitoring app that would be natively integrated into Lokad. Our goal is to offer a 1-click solution to Lokad-powered merchants to allow them to obtain their competitors’ prices. If you happen to know such a solution that you would like to see implemented in Lokad, don’t hesitate to forward this post to a relevant contact. If you happen to work in such a company, well, read on.

Salescast and Priceforge have been merged

Innovation is a messy process. If we knew the final destination from the start, the path to getting there would be a lot less convoluted. Lokad is no exception. Over the last year, we constantly kept innovating, right from the beginning of the year as far as inventory forecasting is concerned, and have moved on to pricing optimization more recently. And along the way, we introduced a series of apps, Salescast and Priceforge being the most important ones.

Advance scheduling of your forecasting reports

It was already possible to schedule the refresh of an inventory forecasting report through the usage of a WebCron, however, the actual walkthrough was somewhat convoluted. Thus, we decided to make things simpler, and starting from today, Lokad supports a built-in integration with EasyCron.com. The Configure Project section has been expanded with a new subsection named Schedule the project runs as illustrated in the screenshot below. In order to get started, you should start by opening an account on EasyCron.

Local management of inventory settings

As far as data management is concerned, Lokad’s philosophy is to keep data centralized in the original business app whenever this is possible. We do not want to be an ABC management software (replace ABC by commerce, warehouse, store or entreprise), because our clients already have this software in place. Yet, it is not always possible - or practical - to stick to this principle; so we need to adjust.

Unleashed Software natively supported by Lokad

A few weeks ago, we announced our native support for Vend, a very nice POS app coming from New Zealand. Today, we are proud to announce that Lokad also provides native support for Unleashed Software, another great piece of software, and also from New Zealand! Unleashed Software delivers a powerful inventory SaaS service, and thanks to their great API (Application Programming Interface), it is now possible to import all the relevant data into Lokad in one single click.

Scheduling your Salescast executions

Update 2015-02-10: we have now a built-in WebCron integration which is now the approach we recommend as it is more secure. Inventory optimization should be business as usual. Yet, Salescast, our inventory forecasting app, does not natively support scheduled executions yet. However, it is possible to obtain scheduled executions with 15min setup. In order to do that, we are going to combine the API of Salescast which offers a programmatic control on Salescast with webcron service.

Orchestrating Priceforge projects with Salescast

One of our key goals for 2015 is to deliver a better integration of our apps, namely Salescast and Priceforge, so that it feels like using Lokad rather than using Salescast plus using Priceforge. The built-in dashboards of Salescast were already a step in this direction, and today, we take another step. It’s now possible to configure a Salescast project to execute a specific sequence of Priceforge projects. Just go to the Priceforge runs section within the configuration view of your Salescast project to get started.

Vend natively supported by Lokad

This list of apps natively supported by Lokad is growing, and today, we are proud to announce that our native support (beta) for Vend is live starting from today. Vend is a very nice POS software, very affordable too, and, and we have been impressed by the overal level of polish for all the parts of the app (technical documentation included!). Managing a couple of outlets via Vend? Now, in just a few clicks, you can connect your Lokad account to your Vend account, and get inventory forecasting reports, pricing optimization and overall commerce intelligence through Lokad.

New pricing based on business turnover

Our last major pricing evolution took place almost 2.5 years ago, and since that time, Lokad has been making steady and constant progress in developing its business. As a result, our old pricing had simply become out of sync compared to what Lokad has become; and an extensive revision was long due. Originally, Lokad only had a single app Salescast. Then, we introduced BigFiles - a file hosting service, followed by Sync - our data integration service and finally, we released Priceforge, a full-fledged data processing engine.

Built-in dashboards for Salescast

For years, Salescast has been delivering the best demand forecasts we could compute, but from the user experience angle, Salescast was plain, very plain. For every product or SKU, you would get the reorder point and the reorder quantity; and that was it. Over the last couple of months, we have been steadily developing new ways to have our apps working better together, and today, we are happy to announce that Salescast now delivers built-in dashboards.

Auto-refresh your data from Salescast

The user interface of Salescast had barely changed since the last major upgrade we shipped two years ago. However, under the hood, Salescast had been undergoing steady changes to improve reliability and performance. This summer, we released native support for Brightpearl, Linnworks and TradeGecko. However, those new capabilities of Lokad were not integrated into Salescast, and, as a result, generating a new forecast report required 4 steps: Go to Sync in Lokad, and trigger a refresh.

Job: Quantitative Business Analyst

Once again the Lokad team needs to expand. This time we are seeking a quantitative business analyst. Job description Your goal will be to drive commerce companies - our clients - to improve their performance when tackling a variety of quantitative challenges such as inventory forecasting or pricing optimization. In order to achieve this goal, you will benefit from the technologies that Lokad has developed, and you will also benefit from a direct mentoring from the Lokad founding team.

Inventory forecasting for Aerospace

While the core focus of Lokad’s activity has been on commerce since the very beginning, over the years, we have also delivered forecasts and optimized stock levels for a variety of other verticals. Some verticals prove to be more challenging than others as far forecasting is concerned, and the aerospace industry with its low rotations, its highly expensive parts and its costly stock-out incidents - i.e. grounded aircrafts waiting for a missing part - is certainly one of the most challenging verticals in terms of forecasting.

Book: Quantitative Commerce Optimization

We have just released a book! Quantitative Commerce Optimization with Envision and Priceforge Our app Priceforge has been designed to support all kind of commerce centric data calculations and data visualizations. While it started with a focus on pricing, it can do a lot more. This book is addressed to commerce executives and commerce analysts who want to harness the power of technology to bring their company to the next stage of profitability.

Top 10 Oddities in Demand Forecasting

Statistical forecasting is a highly counter-intuitive field. And most assumptions which may seem intuitive at a first glance, turn out to be plain wrong. In this post, we compile a short list of the worst offenders among all the statistical oddities that make the bread and butter of Lokad’s business. 1. Advance forecasting systems DO NOT learn from their errors Forecasting systems typically refresh their forecasts on a daily or weekly basis.

New video for Priceforge

Priceforge is both a pricing engine and a dashboarding engine. It was already a cool app, and now it has a cool video too. More materials are coming, stay tuned!

Lokad is hiring: junior and senior developers

Business is growing and moving fast. A few weeks ago we moved to new offices twice as large as the previous ones. More than ever, we are seeking talented software developers. We have two open positions in Paris: a junior and a senior. While working with us, you will focus on big data apps. We are technology-driven company. We pay a lot of efforts in crafting highly interesting (and challenging too) bits of technology.

Mitigating supplier stockouts

Most inventory optimization processes are approximate in the sense that the propensity of the suppliers to face a stockout is not modeled. This approximation simplifies a lot the analysis, and as long suppliers have service levels that are substantially higher than the target service levels of the downstream retailer, distortions introduced in the inventory analysis are minimal. However, if the retailer seeks service levels higher than the ones offered by its supplier, then things get more complicated, and a lot more expensive inventory-wise too.

Faster and better Priceforge

Over the last couple of weeks, we have deployed several incremental releases for Priceforge, our pricing optimization webapp. Below, we review some of the latest additions. Faster data import. Our parsing logic has been largely rewritten for better performance. The app is now loading the data at roughly 30MB/s when processing large flat files. This is about 8x faster than our initial implementation. Better development UI. The code editor now displays in the sidebar the types of the columns loaded from the flat files, as inferred from the Envision script itself.