Date: Sunday, April 6, 2025
Time: 1:00 PM - 2:45 PM
Where: Room 203
Accessibility: Free and open to all conference registrants
Presenter: Nicole Misek
Staff: Haley Eshagh, David Yeiser
Why did the optimization model pick this solution vs. another? How does the decision model perform under this range of conditions? How do I compare my plan to what the model chose? What is the best way to reproduce past model runs? Questions such as these are inherent to the journey to build, deploy, and advocate for decision models.
This session will cover selected discussion points that arise throughout the decision model lifecycle that are often challenging to address using traditional approaches. With DecisionOps, we’ll explore how more efficient methods for running decision models on remote infrastructure, simulating “what if” scenarios, reproducing past runs with a streamlined “replay mode”, setting up decision pipelines to automate workflows, and drive cohesive collaboration to catalyze stakeholder buy-in.
Join us for this interactive session that will demonstrate these workflows, allow for hands-on experimentation, and Q&A. This session is relevant to anyone working with tools such as: OR-Tools, Pyomo, HiGHS, VROOM, Gurobi, AMPL, Hexaly, Jupyter Notebooks, Plotly, Statsmodels, Prophet, and more.
Date: Monday, April 7, 2025
Time: 1:50 PM - 2:40 PM
Where: Room 201
Accessibility: Free and open to all conference registrants
Presenter: Carolyn Mooney
Staff: Haley Eshagh, Nicole Misek
Optimization is founded upon the promise of efficiency and improving solutions. While it’s reasonable to believe project success starts and ends with a decision model’s runtime, there are greater efficiency hurdles to be had beyond the Big M or a destroy operator. In today’s analytics environment, the leading teams will be defined by how they apply DecisionOps practices to test, deploy, and operate these solutions alongside software and business stakeholders.
Join this session to learn basic concepts, real-world applications, and how to get started with DecisionOps in Nextmv, a platform for accelerating decision model development. This session is relevant to anyone working with tools such as: OR-Tools, Pyomo, HiGHS, VROOM, Gurobi, AMPL, Hexaly, Jupyter Notebooks, Statsmodels, Prophet, and more.
Date: Tuesday, April 8, 2025
Time: 3:40 PM - 4:30 PM
Where: JW Grand 1
Accessibility: Free and open to all conference registrants
Presenter: Carolyn Mooney
Staff: Haley Eshagh, Nicole Misek
A mentor of mine once said, “Your model provides no value until it’s in production and making decisions. Until then it’s simply a cost.” These words should carry weight for anyone building decision models: while optimization modeling is your specialty and craft, operationalizing models into live processes is likely not.
Going “live in production” where your decision model’s plans have real-world impact is a collaborative process that is made more efficient by integrating with software engineering tools practices. DecisionOps is a set of practices, tools, and infrastructure for operationalizing decision models quickly, consistently, and reliably.
Join this session to learn about each piece of the DecisionOps workflow and how to get started through real-world applications and storytelling. We’ll cover integrating models as microservices, monitoring and observability for performance, testing for model validation and rollout quality, CI/CD workflows, and reporting and interactive visualization to promote stakeholder understanding and buy-in.
