Exhibitor Workshops

Please note: Exhibitor Workshops are part of the preconference programming. As such, they may include product demonstrations and be commercial.

Sunday, April 12

From Complexity to Clarity: Driving Better Decisions with AnyLogic Simulations
Presented by: Saurabh Parakh and Martin Franklin

9-10:45am | Magnolia 3

Description

MOSIMTEC will demonstrate how AnyLogic Simulation Software enables organizations to make faster, smarter, and more confident decisions in increasingly complex environments. As businesses face growing uncertainty across supply chains, manufacturing, logistics, and service operations, traditional analysis methods often fall short. This session will showcase how multimethod simulation: combining discrete event (DES), agent-based (ABS), and system dynamics (SD) modeling, provides a powerful, flexible approach to understanding real-world systems.

Through practical examples and live demonstrations, attendees will see how AnyLogic models capture variability, interdependencies, and human behavior to reveal insights that static tools cannot. We will highlight how companies are using simulation to reduce risk, optimize performance, and evaluate strategic scenarios before making costly investments.

Participants will leave with a clear understanding of why AnyLogic stands out as a leading simulation platform; scalable, visually intuitive, and capable of integrating with real data and enterprise systems. Whether you are new to simulation or looking to enhance your current analytics toolkit, this session will provide actionable insights into leveraging simulation as a competitive advantage.

Getting Optimization into Production: From Prototype Models to Operational Decision Systems
Presented by: Christian Valente, Jurgen Lentz, and Juan Bohorquez

11am-12:45pm | Camellia 3

Description

Optimization models often begin as small analytical prototypes but become much harder to deploy as they grow into operational decision systems. As models scale, teams encounter new challenges related to model structure, system integration, solver performance, and maintaining reliable workflows in production environments.

This exhibitor workshop demonstrates how optimization applications evolve from simple models to scalable decision systems. Using a power generation portfolio optimization example, we begin with a basic linear programming model and progressively expand it toward a more realistic industry application.

As the model grows in complexity, we highlight common barriers that arise when moving optimization into production environments, including model maintainability, integration with analytics systems, solver performance and feasibility management, and stakeholder trust in decision models.

Participants will see how these challenges can be addressed through practical modeling patterns, solver strategies, and system integration approaches. The session will also illustrate accessible on-ramps for getting started with optimization and how those approaches can scale into robust production deployments.

By the end of the workshop, attendees will have seen how a simple optimization model can evolve into a more realistic decision application while overcoming several common barriers to operational deployment.

Model and Solve Nonlinear Optimization Problems with Artelys Knitro
Presented by: Louis-Pierre Campeau

11am-12:45pm | Camellia 1

Description

Artelys Knitro is the leading solver focused on large-scale, nonlinear (potentially non-convex), optimization problems. Knitro offers both interior-point and active-set algorithms for continuous models, as well as tools for handling problems with integer variables and other discrete structures. This tutorial will introduce the key features of Knitro and demonstrate how to use Knitro to model and solve optimization problems in various environments. The talk will showcase several instances of nonlinear problems, typically addressed through linear relaxation, yet warranting a direct approach. It will delve into the methodologies and tools employed to tackle these challenges. This tutorial aims at an audience familiar with the basics of mathematical optimization and Python programming but will mostly be focusing on practical examples.

Accelerating Time-to-Value with Explainable AI and Agentic Decision Workflows
Presented by: Amit Garg and William Lopez

11am-12:45pm | Camellia 2

Description

Across industries, organizations are increasingly adopting advanced optimization to enhance planning, scheduling, and operational performance. As these models become more powerful, the next frontier is enabling decision-makers across the enterprise to interact with optimization systems seamlessly and translate insights into everyday operational decisions.

This workshop introduces the architecture and implementation of an AI-powered Decision Intelligence platform developed by ORMAE that combines mathematical optimization with Explainable AI and agentic decision workflows. The platform integrates optimization engines with conversational interfaces, explainability layers, and event-driven agents that respond dynamically to changing operational conditions.

Participants will explore how planners and business users can interact with optimization systems using natural language, rapidly generate scenarios, and understand the reasoning behind recommended decisions. The session will include a live demonstration and hands-on walkthrough of an AI-driven optimization application, illustrating how optimization models can be operationalized as interactive decision tools within enterprise workflows.

Attendees will leave with a practical framework for deploying explainable, adaptive optimization systems, accelerating time-to-value and expanding the role of decision intelligence across supply chains, industrial operations, and enterprise planning environments.

SAS Analytics and Quantum Computing
Presented by: Rob Pratt and Yan Xu

11am-12:45pm | Magnolia 3

Description

SAS offers extensive analytic capabilities, including machine learning, deep learning, natural language processing, statistical analysis, optimization, and simulation. SAS analytic functionality is also available through the open, cloud-enabled design of SAS® Viya®. You can program in SAS or in other languages – Python, Lua, Java, and R.

This workshop will review the SAS analytics portfolio, highlight recently added optimization features, and explore several optimization examples, including an application where quantum computing yields performance improvements.

Academic faculty, staff, and students can access the latest SAS software through our free academic software platforms SAS Viya for Learners and SAS Viya Workbench for Learners. Access instructions and learning resources will be provided.

Beyond Narratives: Making LLM Knowledge Computable with Bayesian Networks
Presented by: Stefan Conrady

1-2:45pm | Camellia 3

Description

Recent advances in large language models (LLMs) have made vast amounts of domain knowledge accessible in natural language form. However, this knowledge remains implicit, unstructured, and difficult to operationalize for rigorous analysis or decision support. This workshop introduces a novel methodology for transforming language-based knowledge into explicit, simulation-ready causal models.

Using BayesiaLab and its subject-matter assistant, Hellixia, participants will see how knowledge derived from LLMs can be combined with empirical data and human expertise to construct Bayesian networks. The approach translates high-level, language-based abstractions into formal variables, causal relationships, and probabilistic dependencies, yielding transparent models that support causal inference, scenario analysis, and decision optimization.

Following this introduction, the workshop presents a supply chain case study that demonstrates the end-to-end workflow. Starting from a business question, participants will observe how LLM-informed knowledge is structured, refined, and integrated with data to produce a fully operational model.

By making implicit knowledge explicit and computable, this methodology enables a new class of analytics workflows that bridge generative AI and causal modeling. The resulting models are interpretable, auditable, and directly applicable to complex decision-making problems across domains.

Scaling Adaptive Workforce Optimization: How ATALIAN and DecisionBrain Replaced Manual Scheduling with Real-Time Intelligence
Presented by: Tom Heyward

1-2:45pm | Magnolia 3

Description

Airport cleaning operations run against one of the most demanding scheduling environments in facility management — shifting flight schedules, unpredictable passenger flow, and cascading task dependencies that render static daily plans obsolete within hours. This workshop presents how ATALIAN, a global leader in facility management, partnered with DecisionBrain to replace manual coordination with a dynamic, closed-loop scheduling system powered by the DB Gene platform.

Attendees will see how real-time external data — including live flight information and zone-level crowd distribution — feeds directly into optimization logic to continuously revise workforce schedules as conditions evolve. We walk through a three-tier decision support model serving managers, supervisors, and frontline agents, and examine how role-specific workflows drove adoption across the organization.

Beyond the airport context, the session draws out the transferable principles: how situation-aware constraints, automated re-scheduling, and real-time execution tracking apply across any workforce-intensive environment facing volatile demand.

Participants leave with a practical framework for evaluating the transition from static, experience-dependent planning to standardized, AI-driven workforce optimization — and a clear picture of what production-ready decision intelligence looks like at enterprise scale.

Bridging Optimization and Machine Learning: An Exploration with GAMSPy
Presented by: Adam Christensen & Steven Dirkse

1-2:45pm | Camellia 1

Description

This workshop introduces GAMSPy – a powerful mathematical optimization package that merges the high-performance GAMS execution system with the flexibility of the Python language. The result is a complete mathematical optimization package that can be deployed anywhere – effortlessly.

Join us to explore GAMSPy’s fundamental functionalities through practical exercises. We’ll cover everything from defining sets, parameters, variables, and equations to solving models and retrieving results, all within a familiar Python environment. Beyond the basics, we’ll also provide a glimpse into more advanced features, demonstrating how GAMSPy can streamline complex modeling workflows and enhance your analytical capabilities.

A major focus of the session is the intersection of optimization and Machine Learning (ML). We will explore essential GAMSPy ML functionality – such as formulations for neural network layers, activation functions, and regression trees. These tools enable users to implement sophisticated constructs directly within their optimization models, offering flexibility across diverse use cases.

Whether you’re a seasoned GAMS user looking to integrate with Python or a Python user curious about optimization, this workshop will equip you with essential skills needed to get started and demonstrate what is possible with GAMSPy.

Want Your Decision Project to Succeed? Treat it Like Software
Presented by: Nicole Misek and Ryan O’Neil

1-2:45pm | Camellia 2

Description

Decision models drive significant ROI in cost savings, carbon emissions, customer satisfaction, personnel safety, and more. But there are overlooked inefficiencies outside the solver that compound during development, eroding stakeholder trust and confidence. And when it comes time to plug your model into software architectures, the project flounders and fails.

Much of OR training and education has traditionally focused on the elegant and powerful math driving decision models. More recently, leaders within the community are realizing that a software-conscious mindset is necessary for the discipline’s success. The good news: The tools and practices best suited to address this gap are more accessible than ever before.

This session will cover how to leverage the Nextmv platform to easily incorporate DecisionOps into OR and decision science projects. We’ll walk through hands-on exercises that demonstrate using an open source framework for structured local model development that can progress into robust model management, versioning, monitoring, testing, collaboration, and orchestration.

Throughout, you’ll see how to engage stakeholders efficiently by comparing individual model runs, performing scenario tests, comparing multiple models, and seamlessly integrating into the larger decision stack.

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, FICO Xpress, NVIDIA cuOpt, IBM CPLEX, CVXPY, and more.

Unlocking Business Value with the Latest from FICO® Xpress Optimization
Presented by: Carlos Zetina

3-4:45pm | Camellia 1

Description

In recent years, the scope and responsibilities of optimization Data/Decision Science (DS) teams continue to expand beyond simple model formulation. DS teams are now closely involved in the deployment, monitoring, and maintenance of the optimization models they develop.

In this session, we’ll explore how FICO Xpress Optimization facilitates collaboration among DS teams, engineers, and business users as they build end-to-end enterprise solutions using the latest technology and advances in the field. We’ll also demonstrate how FICO Xpress accelerates “time-to-value” with its state-of-the-art solver, robust modeling and programming interfaces, and its low-code/no-code application development and deployment platform.

Beans, Bots & Better Solutions: A Gurobi Workshop
Presented by: Xavier Nodet, Lindsay Montanari, Everett Dutton, and Anna Collins

3-4:45pm | Magnolia 3

Description

Join us for an engaging and informative session that highlights the latest innovations and practical techniques across the Gurobi ecosystem. We’ll kick off with a brief welcome and agenda overview, along with pointers to other must‑see Gurobi sessions. Next, get introduced to Gurobean, with an overview of its purpose and capabilities from the team behind it. We’ll then dive into heuristics and strategies for finding high‑quality solutions early, focusing on approaches you can apply to improve performance and results in real-world models. The session continues with updates on Gurobot and a walkthrough of other new features, showcasing how these tools can enhance productivity and model understanding. We’ll wrap up with an open Q&A, giving you the chance to ask questions and connect the dots across the topics covered. Whether you’re looking for new tools, practical insights, or what’s coming next, this session offers something for every Gurobi user.

Hexaly, Hybrid Optimization Solver
Presented by: Fred Gardi

3-4:45pm | Camellia 2

Description

Hexaly is a new type of global optimization solver. Its modeling interface, accessible in Python, Java, C#, and C++, is hybrid, unifying concepts from mixed-integer programming, nonlinear programming, constraint programming, and black-box optimization. As a result, it is nonlinear, set-oriented, and supports user-coded functions, enabling seamless integration of simulation with optimization or machine learning with optimization. Under the hood, Hexaly combines exact and heuristic optimization methods: spatial branch-and-bound, simplex methods, interior-point methods, constraint propagation, automatic branch-cut-price, local search, surrogate modeling, among others.

Hexaly stands out from traditional solvers by delivering super-fast solutions to discrete optimization problems such as routing, scheduling, sequencing, packing, picking, clustering, matching, assignment, balancing, and location problems. For example, Hexaly provides solutions close to the best-known results in the literature for vehicle routing problems with thousands of points and job shop scheduling problems with millions of tasks, in just 1 minute of runtime on a basic laptop.

In addition to the Optimizer, Hexaly offers an innovative platform called Hexaly Studio, designed to prototype, develop, and deploy optimization applications quickly in a low-code fashion. This web-based platform is also well-suited for educational purposes; like all other Hexaly products, it is free for faculty and students.

No-code Machine Learning with JMP Student Edition and JMP Pro
Presented by: Ross Metusalem

3-4:45pm | Camellia 3

Description
You don’t have to write code to build modern, powerful machine learning models. JMP Student Edition (free for academic use) and JMP Pro are desktop software applications that provide an interactive, point-and-click interface for predictive modeling, clustering, and dimensionality reduction, as well as specialized techniques including image classification and text mining.

The first hour of this workshop will focus on predictive modeling. You’ll learn how to use JMP software to:

Build predictive models using neural nets, tree-based methods, and other algorithms.

Perform automated cross-validation and hyperparameter tuning.

Explore models with interactive graphics.

Easily fit and compare multiple competing models.

Deploy models in JMP and other software environments.

The remainder of this workshop will highlight JMP tools for a selection of additional techniques:

Clustering,

Image classification, and

Integrating JMP and Python to combine capabilities from both.

Learn more about JMP software capabilities at jmp.com/capabilities, and get full-featured, free JMP software for academic use at jmp.com/student.

Exhibitor Workshops

Sunday, April 12

Get the Latest Updates