Blog

6 best practices for operationalizing decision models from local dev to production

A look at how to action a handful of best practices derived from experience and observation intended to improve decision model success.

Nextmv Pyomo integration: Build, test, deploy Python-based decision models faster

Do you model optimization problems with Python and Pyomo? The Nextmv Pyomo integration makes it easier than ever to run, test, and deploy Pyomo models using Nexmv’s DecisionOps platform.

Should I use map or traffic data for my vehicle routing problem (VRP)?

When planning routes for vehicles, it’s reasonable to think you want to incorporate map or traffic data. But it’s not always needed and is often an investment if you decide to pursue it. We look at how to decide.

Community conversation with founders at Ox and The Rounds

How do logistics and automation intertwine? What are common misconceptions about decision automation? How do efficiency and sustainability power the circular economy? We asked startup founders these questions and more.

Nextmv 1.0: Accelerate decision model development with a DecisionOps platform

Our first major version has landed – merging tools for building, testing, deploying, and managing decision models into one platform. Ship more models, rapidly iterate and improve, and make greater operational impacts with Nextmv.

How to set up CI/CD for an OR-Tools CVRP model using Nextmv DecisionOps tools

We explore continuous improvement for a Google OR-Tools decision model using testing techniques at each stage of the development lifecycle and GitHub.

What is switchback testing for decision models?

It’s time to understand the behavioral impacts of a new decision model under real-world conditions compared to a production model. Switchback testing enables this, helping build confidence in a new model’s rollout in a safe and measured way.

8 new things you can do in the Nextmv console for DecisionOps

From configuring model options to performing experiments on subscribed apps, there’s a whole lot more you can do in the Nextmv console to accelerate the development of your decision algorithms.

Kale AI on last-mile cargo bike operations and a greener urban logistics future

A look at how one startup is supporting sustainable and resilient city design by optimizing urban delivery logistics — starting with dispatch apps designed for eco-friendly operators.

Assign workers to shifts with a low-code scheduling app

In a few clicks, you can spin up, configure, and run a Nextmv decision app that assigns workers to flexible or fixed shifts. Use a unique API endpoint to automate shift scheduling for delivery, healthcare, education, retail use cases, and more.

Reflecting on one year of the Nextmv platform

It’s been one year since we launched the new and improved Nextmv platform. That was just the start of an exciting dash to arrive at the product we have today. We’ve come a long way, and there's so much more to come.

The Nextmv OR-Tools integration: Quickly deploy and test OR-Tools models

We’re thrilled to announce our integration with OR-Tools – pairing production-ready infrastructure, version management, and testing capabilities with the modeling libraries and solvers you know and love.

To change my decision model, or not? That’s not a question. It’s a test.

Change can be scary or energizing. But when it comes to developing and deploying algorithms that make routing, scheduling, and fulfillment decisions, ready-made testing tools tilt the balance in favor of energizing by building confidence.