วีดีโอ

How do optimization teams get decision models live into business processes faster as managed services? DecisionOps provides a transparent, repeatable, and collaborative workflow for decision modeling and software teams to deploy new and improving decision models that deliver business value. This video walks through industry observations, the components that make up a successful DecisionOps work...

Bringing your Python model to Nextmv allows you to see value faster - weeks or less instead of months. It's as simple as running a command in Python. Watch the full demo: www.nextmv.io/videos/bring-your-custom-python-decision-model-to-nextmv-and-accelerate-time-to-value

Learn how to use the Nextmv Hexaly Integration to seamlessly bring your Hexaly model into the Nextmv platform. This video covers code setup, license instructions, and how to push your decision model to the Nextmv platform to perform model tests, manage versions, and integrate with CI/CD workflows. Learn more at www.nextmv.io.

Learn how to use the Nextmv Python SDK to bring your custom Python decision model to the Nextmv decision science platform. By formalizing a common pattern for getting started with an optimization model, learn how to add your model to Nextmv and simplify handling deployment infrastructure, model validation and experimentation, and more. Learn more at www.nextmv.io

Explore a stochastic production problem through the lens of a sushi featuring Seeker (via InsideOpt) as the solver and Nextmv as the decision model platform. In this example, you'll see how to solve a problem where a sushi restaurant produces different types of products, must balance the cost of production with potential losses or gains (depending on consumer buying), and must adhere to constra...

Traditionally, the operations research discipline has been dominated by deterministic optimization practices. But as machine learning and data science continue to grow within businesses, there’s greater desire to bridge the two fields and incorporate more real-world uncertainty into decision models. In this session, we’ll explore this topic through the lens of Seeker, a new stochastic optimizat...

Scenario testing is an effective way to play out different situations under realistic conditions using historical or synthetic input data before committing to a decision. Scenario tests are configured through Nextmv’s user-friendly UI, runs are executed on scalable remote infrastructure, data instances are easily managed, and results are analyzed using a common, shareable format. Learn more: ww...

Accelerate development of your Python decision models - from completely custom models to those built using popular modeling tools - with features for testing, deploying, managing, and collaborating. www.nextmv.io/blog/bring-your-custom-python-decision-model-to-nextmv-build-test-deploy 00:00 - Intro 00:20 - OR-Tools TSP example 00:37 - Initializing the Nextmv Python template 02:37 - Copy over th...

Many operations research and decision science practitioners start their optimization modeling journey with open source projects such as HiGHS. What is HiGHS? What role does it play in the MIP ecosystem? And how can we accelerate the real-world impact of HiGHS-based decision models? In this session, we explore these questions alongside the HiGHS project developers, Julian Hall and Ivet Galabova....

Learn how to use vehicle activation penalties to encourage vehicle efficiency. This is sometimes known as prioritizing backhaul when going back to a depot. Learn more at: www.nextmv.io/docs/vehicle-routing/features

Learn how to configure your vehicle routing problem (VRP) to have multiple pickups precede a dropoff. In this example, learn how to set two pickups at two different locations precede a dropoff stop for a pickup and delivery problem. Learn more at: www.nextmv.io/docs/vehicle-routing/features

Learn how to model continuous moves for a vehicle going back and forth from a depot. Typically, users restrict to singular moves from a depot to model the distribution problem, where all vehicles have a default start and end location. In this example for continuous moves, we'll instead model the stops array as only the dropoffs, we'll include both a pickup stop and a dropoff stop for each parti...

More and more, data science and decision science practitioners are seeking to combine machine learning forecasts with actionable and optimized decisions. This can include anything from predicting traffic patterns for delivery scheduling to consumer buying behavior for inventory management. But bridging these two disciplines can be challenging. In the on-demand logistics space, these worlds are ...

OR-Tools and VROOM are popular open source options for solving vehicle routing problems (VRPs). Getting visual (and shareable) feedback when developing decision algorithms is critical. Wouldn’t it be nice to be able to plot stops, clusters, routes, and more on a customizable map with just a few commands? Enter: Nextplot, an open source CLI tool for visualizing JSON input/output data. Use Nextpl...

Optimization modeling with AMPL, Streamlit, and Nextmv

Link and test logistics models for demand forecasting, shift scheduling, and vehicle routing

Getting started with DecisionOps for decision science models using Gurobi

Deploy and run custom decision model

Decision model acceptance test

Operationalizing Java-based OR-Tools decision models

Q&A on CI/CD for decision science with Nicole Misek (VP of Engineering)

Nextmv AMPL integration demo

Nextmv Gurobi integration demo

Demo: Java support for the Nextmv OR-Tools integration

Switchback (A/B) testing for decision optimization models

Nextplot introduction: Open source plotting with JSON

Nextplot demo: An open source route visualization tool for JSON

Build, test, and deploy Python-based Pyomo MIP decision models with DecisionOps

What is switchback testing for decision models?