Generating supply chain insights for global enterprises

Descartes Labs is productizing cutting-edge science research built on the Descartes Labs Platform. The Descartes Labs team builds custom solutions that deliver financial and operational advantages, unprecedented in both scope and scale, to customers. We structure solutions to allow any company to derive the most value out of its supply chain through use of our general-purpose machine-learning platform.

Solutions across industries
Government & Defense
Proprietary forecasting models

The Descartes Labs Platform can help organizations unlock the hidden value of their own data in a variety of ways. Our data refinery allows customers to engage with the platform via their own development teams who build their solutions on a do-it-yourself basis or by way of the Descartes Labs team providing full-service development, including spinning up secure instances of our platform, on which special-purpose applications can be built.

Our team includes internationally-recognized experts in machine learning and large-data computation, with decades of experience working in highly rigorous and secure U.S. national labs. We apply the same scientific rigor and security procedures when building you a proprietary solution.

Integrate your data with the Descartes Platform to create your own solutions, models, and forecasts.

Our methodology

Our solutions are driven by models of real-world processes that are fed relevant inputs (e.g., satellite imagery, weather data, price history, market demand, etc.). By simulating the dynamics of the underlying process, we can forecast probable outcomes and help our customers make better decisions. By automatically capturing data from your business and other sources, Descartes Labs can create a model for you that will continuously improve, becoming a more and more powerful asset for your business over time.

  • Define the problems

    We start by understanding your business needs, context, and the available data; we also obtain additional data to improve your model.

  • Wrangle the data

    We resolve inconsistencies between sources and optimize the structure of the data for computational performance. Then we automate these steps, so that new data can be incorporated in real-time.

  • Develop the model

    Before selecting a production model, we rigorously test hundreds or even thousands of candidate models against the historical data set, iteratively improving the model through machine learning.

  • Verify the model

    We expand and run the model to establish the value. We compare and validate candidate model results against historical “truth” and create an accuracy assessment.

  • Deploy for production

    We build models so that you can use them to run your business, every day. Your models and your data live in a private instance of the Descartes Labs Platform. Our platform ensures security and reliability, and it requires no infrastructure management from you.

By automatically capturing data from your business and other sources, your model continuously improves, becoming a more and more powerful asset for your business.