Take advantage of these pre-conference workshops for a hands on demonstration of the latest in Analytics software. All attendees are welcome to join onsite or pre-register. If you’ve already registered for the conference, you can add workshops by editing your record.
Descriptions and times below:
Sunday, April 16
Time:
11am-12:45pm
Location:
Cottonwood 9
Predictive Modeling Workflow using JMP Pro Software
Presented by: Kevin Potcner
Teaching the process of building, evaluating, and choosing statistical models has become an essential part of the curriculum for Analytics Programs. What was once limited to teaching only linear and logistic regression, instructors are now exposing their students to many other modeling techniques – partition/trees, neural network, K-nearest neighbors, Text Mining among many others. Curriculums are also evolving so that students are being exposed to what working on real datasets are like. This includes such steps as cleaning and formatting data, deciding how to deal with missing values and outliers, exploratory analyses, building and comparing a variety of models, deploying the chosen model in a production environment, and presenting results in an accessible manner to a non-technical audience.
In this workshop, a statistical scientist from JMP will illustrate how JMP Pro’s no-code interactive and visual approach to this process can greatly enhance student’s understanding, and enjoyment of the predictive modeling workflow.
Time:
1-2:45pm
Location:
Cottonwood 9
DB Gene: Bring your Optimization Model to the Cloud, Create Dashboards and Connect it with Tableau
Presented by: Giulia Burchi and Filippo Focacci
DB Gene is a development platform to easily customize and deploy cost-effective optimization solutions. It helps reduce development time and costs by over 70%. It allows to quickly create and deploy optimization solutions for business users.
In this workshop, we will leverage a workforce optimization model and we will:
- Deploy it on the cloud,
- Import data from excel and edit it in the web UI,
- Create an interactive and intuitive data visualization with out-of-the-box web user interface widgets,
- Run the model and manage several computation processes in parallel with the tasks server, on-premise, or in the Cloud,
- Compare scenarios and do What-if Analysis, and
- Create a business reporting dashboards using our new Tableau integration.
DB Gene is based on state-of-the-art technologies, easy to find on the market, and allows you to quickly bootstrap an application and make the most of your optimization model.
Time:
1-2:45pm
Location:
Cottonwood 3
Quantum Computing for Optimization
Presented by: Alex Koszegi
Quantum computing has gone from the lab to the enterprise, and a recent Hyperion Research study found that that there already are a wide range of commercial organizations engaged in some form of quantum computing efforts. While you may think production use of quantum computers are years away, the first commercial quantum applications are in production are using D-Wave’s quantum technology.
This workshop will cover the following topics:
- An introduction to quantum computers, quantum annealing, and hybrid solvers
- What kinds of business problems are good candidates for quantum/ hybrid solutions
- Use case examples: how quantum hybrid is being used for optimization applications such as resource scheduling, supply chain logistics, portfolio optimization.
- How quantum systems are programmed, and the tools for developers. This will include live demos and an introduction to Leap, D-Wave’s real-time cloud service. Leap provides access to a portfolio of hybrid solvers, enabling enterprises to address all kinds of business problems that range in size and complexity.
- How to get started with quantum for business.
Time:
1-2:45pm
Location:
Cottonwood 4
Build decision models with confidence: Working with testing in optimization
Presented by: Tiffany (Patella) Bogich
Nobel Prize winner Dr. John Mather once said, “If you do not test it, it will not fly.” These words ring true in the world of testing optimization apps. How does one model perform compared to another? How do solutions change as you add or remove constraints? Based on a number of scenarios, how do I grow or adapt my operations? Does a model or optimization solver perform the way I’d expect before deploying it to production? How does a model or solver perform when faced with real-world data? And this is the short list of questions. However, setting up, implementing, and maintaining a testing framework is often a bespoke buildout or relegated to an aspirational project to get to one day. This workshop will walk you through different types of testing and get you hands-on with an optimization testing toolkit that aims to make testing table stakes for any optimization workflow.
Time:
1-2:45pm
Location:
Cottonwood 8
Modeling and Solving Real World Optimization Problems
Presented by: Robert Ashford, Alkis Vazacopoulos, and Dinakar Gade
In this technology workshop, we will present:
1. ODH is a package for accelerating MIP optimization and extending its range. It runs concurrently and synchronously with a MIP optimizer exchanging information with it. Although ODH was primarily designed to enable MIP optimization to be applied to models too large or difficult to be amenable to the standard commercial MIP optimizers such as CPLEX, or other commercial packages, it also accelerates the optimization of most models that are regularly solved with standard MIP.ODH has been developed by Optimization Direct Inc. over the past 8 years to handle real-world customer models for which standard MIP was not effective. On Optimization Direct’s standard hundred model sub-set of mid-sized models taken from its library of nearly 1000 real customer models, ODH reduces the average optimality gap after two hours to nearly half that found by using CPLEX alone. On the MIPLIB version 7 open set of 29 models to which no integer feasible solution had been found, ODH found solutions to 5 of them in 2 hours. Of the remaining 257 models to which no optimal solution had been proven, ODH found and proved optimal solutions in 13 of them and found better solutions to any that had been previously found in 45% of them. Again, with runs of just 2 hours.
Optimization Direct has customers in the scheduling, telecoms, retail, logistics, and supply chain areas who use ODH. At least three of these have applications that would fail without ODH technology. In January 2022, one said ‘ODH is comparable to the best optimization technology available from anyone on my small models and much superior to any other optimizer on the large ones’. ODH uses a number of heuristics, especially a novel decomposition-based method, and information from a MIP optimizer to feed that MIP optimizer with good solutions. This is made possible by its new thread synchronization technology within which the ODH and MIP threads can work efficiently.
2. Recent Enhancements in FICO® Xpress Solver: Join us to learn about enhancements to the FICO® Xpress Solver. Recent enhancements include performance enhancements to the MILP Optimizer, usability features including modeling optimization with multiple objectives, nonlinear solver enhancements, and how machine learning is used within the Xpress Solver to automatically determine scaling, cutting, and detecting numerical instabilities.
Time:
1-2:45pm
Location:
Cottonwood 1
Simulation from A to 3d
Presented by: Nancy Zupick
We will be covering the basics of how to build a simulation model in Arena. The workshop will demonstrate the usage of the Arena software in creating a simple, discrete-event simulation model as well as discussing the need to define your system and document your objectives and processes before beginning any modeling effort. We will then discuss how to move from simulation to virtual commissioning and emulation of a system in Emulate3d.
Time:
3-4:45pm
Location:
Cottonwood 2
Prescriptive Analytics with AMPL: Learn how you can build optimization applications quickly and reliably, from prototyping to deployment
Presented by: Filipe Brandão and Robert Fourer
Optimization is the most widely adopted technology of Prescriptive Analytics, but also the most challenging to implement. This presentation takes you through the steps of a proven approach that combines the best features of two implementation environments:
- Prototyping in Google Colab using AMPL, a language and system designed for the needs of formulating and validating optimization models
- Deployment using Python-based tools, the most popular environment for building Analytics models into deployable applications
We start by introducing model-based optimization, the key approach to streamlining the optimization modeling cycle and building successful applications today. Then we demonstrate how AMPL’s specialization to model-based optimization is able to offer exceptional power of expression and speed of execution while maintaining ease of use. Recent enhancements to the AMPL language let you write many common logical conditions in an even more natural way, avoiding complicated reformulations. To support the prototyping phase, expanded data handlers facilitate direct import of values in spreadsheet, CSV, JSON, and database formats.
Our presentation next shows how AMPL and Python work together for building optimization into enterprise systems. AMPL fits naturally into the Python framework, installing as an “amplpy” Python package, importing and exporting data naturally from/to Python data structures and Pandas dataframes, and supporting Jupyter notebooks that mix AMPL modeling and Python programming. In contrast to Python-only modeling solutions, AMPL’s Python API offers straightforward, efficient model processing while leveraging Python’s vast ecosystem for data pre-processing, solution analysis, and visualization.
We finish with a deployment example, showing how Python scripts can be turned quickly into Prescriptive Analytics applications using amplpy, Pandas, and the Streamlit app framework. Deployments are supported on traditional servers and in a variety of modern virtual environments including containers, clusters, and cloud machines.
Time:
3-4:45pm
Location:
Cottonwood 1
Calling all OR Heroes: Learn How to Model and Deploy Solutions in 75% Less Time with FICO® Xpress Insight
Presented by: Jeff Day and Dinakar Gade
Join our hands-on workshop to experience how FICO Xpress Insight helps you read data in any format from any source, integrates with your own machine learning and solvers (or Xpress Solver), enables collaboration with business users, deploys decision support or automated solutions in the cloud or on premises —and does it all in 75% less time.
- Get the overview of the great new features of FICO Xpress Solver, Mosel, Workbench, and Insight including optimization with multiple objectives, mixed-integer-programming enhancements, and the newest entrant to our family of solvers: a new global optimization solver for nonlinear optimization problems.
- Learn how you can rapidly deploy Python models with FICO Xpress Insight.
- Discover the new View Designer, which reduces GUI development times from minutes to seconds.
- Experience real-world business examples in which developers integrate their own solver(s) with the powerful Xpress Insight platform.
- See how the flexible, free-to-use Xpress Mosel modeling and programming language allows you to make your solver available to thousands of other Mosel users.
All attendees will receive a link to the complimentary FICO® Xpress Optimization Community License.
Time:
3-4:45pm
Location:
Cottonwood 3
Gurobi 10.0 Helping You to Build, Solve, and Deploy Optimization Models
Presented by: Dan Jeffrey, Xavier Nodet, Zed Dean, and Jerry Yurchisin
In this workshop, attendees will learn about our latest release, Gurobi 10.0, and our open-source Python projects that make it easier for users to build models with machine learning models and pandas. We’ll touch on exciting performance improvements to Gurobi’s core algorithms in Gurobi 10.0. We’ll also highlight features that make the model-building and solving process easier.
In the second half of the workshop, attendees will learn about Gurobi’s experimental, open-source Python packages: Gurobi Machine Learning and Gurobipy Pandas. Gurobi Machine Learning allows users to add trained machine learning models as constraints to Gurobi models. Gurobipy Pandas enables users to easily build Gurobi models from Pandas dataframes.
Finally, we will explore a notebook example that combines machine learning and optimization to demonstrate how to use these new features.
Time:
3-4:45pm
Location:
Cottonwood 8
Take a “Step Class” through The Optimization Solution Development Life Cycle: From Business Understanding to Deployment
Presented by: Robert Randall, PhD, and Irv Lustig, PhD
The development and implementation of an optimization-based solution to make critical business decisions goes beyond building a mathematical model and writing code that embeds that model in software. Before any development, it is important to define the business problem, gather support from various stakeholders, and determine the value proposition of a potential solution. Once these issues are understood, a software solution can be developed, and using best practices before, during and after the software development phase will improve the likelihood of successful deployment.
Based on decades of applied optimization work at Princeton Consultants, we will demonstrate the steps to move through the complete solution life cycle, including:
- the non-technical steps of identifying the right problem to solve;
- a focus on best practices for rapid optimization model and software development using Python and pandas;
- best practices for technical deployment of a solution;
- working with clients to ensure adoption of the solution
Time:
3-4:45pm
Location:
Cottonwood 9
Introduction to WordStat Text Analytics
Presented by: Normand Peladeau
Provalis Research CEO Normand Peladeau will identify the main challenges in the analysis of unstructured text data and demonstrates how Provalis Research’s text analytics software WordStat can help you deal with those challenges and analyze large amounts of text data using exploratory text-mining and quantitative content analysis. He will show you how you can quickly and easily explore very large amounts of text data with advanced topic modeling and other techniques as well as how to build and use dictionaries for automated content analysis.
Time:
3-4:45pm
Location:
Cottonwood 4
DECIDE BETTER: Decision Science for Leaders
Presented by: Matt Brady
How do you decide who to hire, when a project phase-gate has been achieved, or which investment to fund next? Chances are, you rely largely on intuition… susceptible to habits, biases, and, groupthink. What if you could elevate your decision-making…to decide using information. To decide better?
Attend this immersive workshop that covers the strategies, motivations, and techniques via real decision scenarios from the audience. Gain additional hands-on experience by attending our Technology Tutorial (Mon Apr 17, 3:40 – 4:30 pm). Stop by our Booth (#300) during exhibit hours to see the innovative Geography Explorer and API Integration in action, and follow all the progress on LinkedIn. Decide better with Volley.
