Technology Tutorials

Join the conference exhibitors as they discuss innovations and best practices in the field. All attendees are welcome to join these tutorials onsite. Descriptions Below

ABET

Monday, April 27, 3:40-4:30pm
Room: Cottonwood 9

Data Science/Analytics Program Accreditation: Current Status within ABET
Presented by:  Paul Leidig and Barbara Price

To address the significant employer demand for data science/analytics graduates, several institutions have developed diverse baccalaureate data science and/or data analytics programs. To lead to a shared understanding of the data science/analytics discipline; a group representing diverse constituents has been exploring possible accreditation criteria for data science programs. ABET accredits programs in applied and natural science, computing, engineering and engineering technology. This session will discuss the current status of this effort, present a strawman draft of data science program criteria, and discuss next steps.

AMPL

Tuesday, April 28, 10:30-11:20am
Room: Cottonwood 11

Model-Based Optimization + Application Programming = Streamlined Deployment in AMPL

Presented by: Robert Fourer & Filipe Brandão

AMPL supports prescriptive analytics by giving you the advantages of modeling in a specialized optimization environment, together with the power of application development via general-purpose programming.

You formulate optimization model concisely and naturally in AMPL’s modeling language, which promotes rapid development, reliable maintenance, and effective solver benchmarking. Then you embed models and scripts into complex applications by use of AMPL’s interfaces (APIs) for widely used programming languages.

We illustrate model and application development using a single running example, highlighting AMPL’s new platform-independent spreadsheet interface, and AMPL’s API for the popular data science language Python.

AnyLogic

Monday, April 27, 11:30am-12:20pm
Cottonwood 11

AnyLogic: The Most Comprehensive Simulation Modeling Platform for Business and Research

Presented by: Jeffrey Wirtz, Program Support Specialist, AnyLogic North America

In this tutorial, we will discuss how you can leverage unique features of AnyLogic simulation software and AnyLogic Cloud to solve your business challenges or perform scientific research. We demonstrate application of simulation in various domains and demonstrate state-of-the-art technologies that can take your simulation models to the next level in terms of sophistication and usefulness.

Artelys

Monday, April 27, 9:10-10am
Room: Cottonwood 9

North-East electricity markets modeling with Artelys Crystal
Presented by: Violette Berge, Vice President at Artelys Canada, violette.berge@artelys.com

Energy issues are nowadays at the heart of public debate. Understanding the cost and environmental impact of generating electricity is necessary to take both policies and investment decisions. Artelys has been developing its optimization platform Artelys Crystal for more than ten years. Artelys Crystal is dedicated to energy systems modeling and optimization. After carrying out more than a hundred studies in Europe related to the mid- to long-term energy system evolution, Artelys is carrying out an R&D project co-financed by the National Research Council of Canada dedicated to North-American power systems modeling and optimization. This session will introduce our modeling platform and the on-going work on the North-East power markets model.

Artelys

Monday, April 27, 1:50pm-2:40pm
Room: Cottonwood 10

Machine Learning and Nonlinear Optimization with Artelys Knitro
Presented by: Richard Waltz, Senior Scientist, Artelys Corp, richard.waltz@artelys.com

Artelys Knitro is the premier solver for nonlinear optimization problems.  Knitro is designed for general purpose, possibly non-convex, nonlinear optimization models.  This tutorial will highlight some of the work being done using Knitro in machine learning, particularly for nonlinear regression and logistic regression applications.  We will compare Knitro performance on these models with some other common optimization solvers and highlight some of the interfaces and APIs that can be used to solve machine learning models with Knitro.

DecisionBrain

Tuesday, April 28, 1:50pm-2:40pm
Room: Cottonwood 10

A closer look: Enhance optimization models prototypes into fully-developed applications thanks to next-gen IBM DOC

Presented by: Giulia Burchi, Patrice Oms

About next-gen IBM DOC

Next-Gen DOC allows Optimization Model Developers to focus on their competencies while delegating infrastructure and architecture-related issues.

About the Tutorial

In this tutorial, we will show how DOC allows you to:

  • Integrate your Python and Watson Studio models
  • Build a dashboard by configuring ready-to-use components.
  • Quickly move from proof-of-concept to production with multiple deployment options.
  • Monitor the real-time job execution, retrieve information of past runs, check the log and re-run the task in a click.
FICO® Xpress Optimization

Monday, April 27, 10:30-11:20am
Room: Cottonwood 11

End-to-End FICO® Xpress Insight Tutorial: From Data to Decisions for Non-Technical Business Users 
Presented by: Jim Williams

You have a team with a great analytics background. They’ve developed advanced analytical tools using Python, R, or your current optimization solver. They’ve derived crucial insights from your data and figured out how your decisions shape your customers’ behaviors. Now it’s time to put these critical analytical insights into the hands of your non-technical business users.

In this tutorial, you’ll learn how FICO’s Xpress Optimization solutions (including Xpress Mosel, Xpress Workbench, Xpress Solver and Xpress Insight) make it possible to embed your analytic models in business user-friendly applications. See how to supercharge your analytic models with simulation, optimization, reporting, what-if analysis, and agile extensibility for your ever-changing business. Plus, you’ll discover how to use the new View Designer to reduce GUI development times from minutes to seconds.

Frontline Solvers

Tuesday, April 28, 10:30-11:20am
Room: Cottonwood 10

From Models to Cloud Decision Services: Do It Yourself
Presented by: Daniel Fylstra, President

For too long, it’s been too hard to deploy and use an analytic model as part of a line-of-business application. Analytic models written in modeling languages or Excel rarely get beyond the conference room, and when they do, rewrites by developers can take quarters to years. This tutorial describes a better way: Build and test your optimization, simulation, or machine learning model, then instantly deploy it as a secure, cloud-based decision service that IT will appreciate. Use data from line-of-business systems, “point and click” without programming, and take full advantage of “low-code / no-code” tools like Power BI, Power Apps and Power Automate to speed deployment. Perhaps most remarkable, we’ll show how your analytic model results can be used by other existing applications, “point and click” without programming.

GAMS

Monday, April 27, 9:10-10am
Room: Cottonwood 10

Deploying models with GAMS MIRO

Presented by: Steven Dirkse and Adam Christensen (GAMS Development Corp)

Are you developing models and looking for a web-based deployment with visualization of input and output data? Does your enterprise require a graphical user interface so that planners can work more productively, leveraging the full potential optimization brings? During this tutorial we introduce GAMS MIRO, a completely new web interface for your GAMS models. We first explain the fundamental concepts of GAMS and the advantages of using GAMS to build optimization-based decision support applications. We also look at existing options to connect GAMS models to other applications and briefly cover some recent developments. The tutorial centers on the recently-released GAMS MIRO. With its tight connections to GAMS, MIRO allows you to perform data manipulation, scenario management, visualization of the model inputs and results, and much more – all from within the web browser – all by adding a very few annotations to your model. You specify which input and output datasets you want to visualize and MIRO produces a fully functional GUI that can be customized to individual tastes and requirements.

During model/application development MIRO can be launched directly from GAMS Studio or from the command line. To fully illustrate the typical MIRO application development workflow, we also show how to deploy an app so that it is available to an end user.

GAMS MIRO also facilitates the generation, organization, and sensitivity analysis of multiple scenarios of an optimization model. A server version will support additional features: managing multiple optimization models for concurrent users with access management, load balancing, batch configuration and much more.

Gurobi Optimization

Monday, April 27, 11:30am-12:20pm
Room: Cottonwood 10

Improvements in the Gurobi Python Interface

Our new release brings with it several significant improvements to our Python interface. We’ll give you an overview of what was possible before, and what is possible now. We’ll also present several examples that demonstrate the new capabilities.

IBM

Monday, April 27, 3:40-4:30
Room: Cottonwood 10

Infeasibility Analysis is Not Just for Infeasible Models
Presented By: Ed Kotz, Senior Software Scientist, Advanced Support for CPLEX Users, IBM

Several commercial linear and integer programming solvers offer functionality to compute a minimal subset of constraints of an infeasible model that explain the source of the infeasibility.   While this can be useful for quickly  understanding why a large model is infeasible, these “infeasibility explainers” can also be used to explain many other model characteristics that don’t explicitly involve infeasibility, including why constraints are redundant, which constraints prevent improvement of an optimal solution, and whether globally valid cuts derived to tighten the model formulation are correct.  This presentation will first describe the fundamental usage of these infeasibility analysis tools, then describe how to answer questions about linear or integer programming models by reformulating the question as a related, infeasible model.   This can be very helpful for developing and troubleshooting models, as well as improving the model formulations to obtain faster or more accurate performance.

International Institute for Analytics

Tuesday, April 28, 11:30am-12:20pm
Room: Cottonwood 11

Variables of Analytics Success – Insights and Attributes from a Decade of Research

Presented by: Drew Smith, VP, Analytics Leadership Consortium, IIA

Over a decade, the IIA has assessed the analytics maturity of hundreds of Fortune 1000 companies, led thousands of hours of enquiries with thought leaders addressing firm specific analytics challenges, and had hundreds of in-depth engagements with analytics executives. Through this volume and variety of data points we have discovered 5 attributes which firms need to continuously nurture and develop in order to move from playing with analytics to establishing market leading positions through analytics. And while we see differences across industries and stages of analytics development, these 5 attributes are industry, firm and stage agnostic. In this talk, Drew Smith will share the origins of the discovery of these 5 attributes, as well as case examples of how firms who are driving on these attributes are delivering business value and market leadership.

JMP, a Division of SAS

Monday, April 27, 10:30-11:20am
Room: Cottonwood 10

JMP and the Predictive Modeling Workflow

Presented by: Kevin Potcner

The amount of data that the modern data analyst has access to continues to grow. This provides a great opportunity for analysts to utilize some of the more modern predictive modeling techniques. A typical real-world predictive modeling workflow includes data cleaning and exploration, model fitting, model validation, model comparison, final model selection and deployment of the final predictive model.

In this session we illustrate the predictive modeling workflow by analyzing a real dataset. After data preparation and initial exploration, we will create a number of predictive models such as multiple linear regression, regression tree, Neural Net, and K-Nearest Neighbors.

We will “publish” each of the models to the Formula Depot, and explore and select the best model using the Prediction Profiler and JMP’s Model Comparison tool. Code will be created in a variety of programming languages (e.g., SAS, SQL, Python, et al.) in order to implement that model in a production environment.

LINDO Systems, Inc. 

Monday, April 27, 11:30am-12:20pm
Room: Cottonwood 9

Optimization Modeling Tools from LINDO Systems

Presented by: Mark Wiley 

Exceptional ease of use, wide range of capabilities, and flexibility have made LINDO software the tool of choice for thousands of Operations Research professionals across nearly every industry for over 30 years. LINDO offers solvers to cover all your optimization needs. The Linear Programming solvers handle million variable/constraint problems fast and reliably. The Quadratic/SOCP/Barrier solver efficiently handles quadratically constrained problems. The Integer solver works fast and reliably with LP, QP and NLP models. The Global NLP solver finds the guaranteed global optimum of nonconvex models. The Stochastic Programming solver has a full range of capabilities for planning under uncertainty.

Get the tools you need to get up and running quickly. LINDO provides a set of intuitive interfaces to suit your modeling preference.

· What’s Best! is an add-in to Excel that you can use to quickly build models that managers can use and understand.

· LINGO has a full featured modeling language for expressing complex models clearly and concisely, and it has links to Excel and databases that make data handling easy.

· LINDO API is a callable library that allows you to seamlessly embed the solvers into your own applications.

Pick the best tool for the job based upon who will build the application, who will use it, and where the data reside. Technical support at LINDO is responsive and thorough – whether you have questions about the software or need some modeling advise. Get started today. Visit our booth or www.lindo.com to get more information and pick up full capacity evaluation licenses.

MemComputing, Inc. 

Tuesday, April 28, 11:30am-12:20pm
Room: Cottonwood 10

Solving Integer Linear Programming Problems with MemComputing

Presented by: Fabio Traversa

A brief introduction to MemComputing followed by a live tutorial of the MemCPU™ XPC SaaS as applied to complex optimization problems compared to best in class solvers. 

Optimization Direct

Monday, April 27, 1:50-4:40pm
Room: Cottonwood 11

Optimization and Machine Learning: An ODH|CPLEX Python primer

Presented by: Robert Ashford & Alkis Vazacopoulos

This short tutorial shows participants how to build a basic model using the DOCplex API in Python. This session includes setting the Python environment, reading data from a CSV or spreadsheet, creating variables, objective functions, constraints, solving the model, and returning the results. Additionally, this session points the participants to further reading so that they may expand their capabilities. Furthermore, we will present the brand new ODH|CPLEX API for Python, which improves solution times for large models.

Princeton Consultants

Tuesday, April 28, 9:10-10am
Room: Cottonwood 11

End User Responsive Analytics: A Python Lightweight Server Framework

Presented by: Irv Lustig, PhD Optimization Principal Princeton Consultants

The end users of many analytics applications want to press the “Solve” button in a browser-based application and get a quick response to their business challenge. For example, an end user may want to spend at most a few seconds to create a production schedule for a business operation, or quickly assign people to jobs. Princeton Consultants has built a lightweight Python framework that simplifies the delivery of the back-end server for such applications. This avoids the complexity of other frameworks that are more suited for applications where the analytics process is computationally expensive. In this tutorial, we will demonstrate our best practices for developing analytics applications in terms of processes, Python libraries, and development tools, using optimization as a motivating example.

Provalis Research

Tuesday, April 28, 9:10-10am
Room: Cottonwood 10

Text analytics and data science: a marriage of convenience?

Presented by: Normand Peladeau

Text analytics borrows techniques from many disciplines, from information sciences, statistics and data sciences to artificial intelligence and computational linguistics. This marriage of techniques is not done without compromises that can lead to sub-optimal applications. During this presentation, you’ll gain insights into:

  • The factors behind these incompatibilities
  • Examples that include the questionable borrowing of techniques from these and other sciences
  • How to be a better text analytics user by taking into account these warnings

Become a savvier user of text analytics tools

Purdue University

Tuesday, April 28, 4:40-5:30pm
Room: Cottonwood 10

Integrating Predictive & Prescriptive Analytics in R

Presented by: Matthew Lanham, Clinical Assistant Professor of Management, Quantitative Methods

Bio: Professor Lanham is a member of the Quantitative Methods Area faculty in Purdue University’s Krannert School of Management. His primary focus is serving as Academic Director for the M.S. in Business Analytics & Information Management (BAIM) program, coordinating and teaching Krannert’s Data Mining, Predictive Analytics, Using R for Analytics, and Industry Practicum courses, as well as interfacing these activities with Purdue’s Business Information and Analytics Center (BIAC) serving as its Assistant Director of Student Engagements. Please visit MatthewALanham.com for work his students have done with industry partners – you just might be persuaded to connect with him to scope out a project yourself.

Rockwell Automation

Monday, April 27, 9:10-10am
Room: Cottonwood 11

Simulation Analysis using Arena

Presented by: Melanie Barker & Nancy Zupick

Rockwell Automation’s Arena simulation software has been one of the leading discrete event simulation packages for over 30 years. If you’re new to simulation or it’s been a while, this session will help you understand when and why to use simulation as opposed to other analysis techniques. We’ll talk about what you need to do to have a successful simulation project, and what potential pitfalls lie ahead. If you are an experienced Arena user, please join us for a special sneak peak at the latest version of Arena featuring our new interface!

SAS

Monday, April 27, 10:30-11:20am
Room: Cottonwood 9

Building and Solving Optimization Models with SAS

Presented by: Rob Pratt, Senior R&D Manager Ed Hughes, Principal Product Manager SAS provides comprehensive data and analytic capabilities, including statistics, data/text mining, forecasting, and operations research methods: mathematical optimization, discrete-event simulation, and project and resource scheduling. The OPTMODEL procedure from SAS provides a powerful and intuitive algebraic optimization modeling language, with unified support for linear programming, mixed integer linear programming, quadratic programming, nonlinear programming, constraint programming, local search optimization, and network-oriented optimization models.

We’ll demonstrate PROC OPTMODEL, highlighting its newer capabilities and its support for standard and customized solution approaches. We’ll also show how you can access SAS optimization capabilities from other programming languages like Python, Lua, Java, and R, thanks to the open, cloud-enabled architecture of SAS® Viya®.

Simio Simulation & Scheduling Software

Monday, April 27, 1:50-2:40pm
Room: Cottonwood 9

Simulation and Scheduling Software All in One!

Presented by: Renee Thiesing and Katie Prochaska (Simio LLC)

Simio is a premier simulation and scheduling software that allows you to expand traditional benefits of simulation to improve daily operations. In this tutorial, we will demonstrate Simio’s 3D rapid modeling capability to effectively solve real problems. Explore how a single tool can be used to not only optimize your system design, but also provide effective planning and scheduling. Come explore the Simio difference and see why so many professional and novice simulationists are changing to Simio.

Stukent

Monday, April 27, 3:40-4:30pm
Room: Cottonwood 11

Use AI and Auto-grading to Help Students Turn Messy Marketing Data into Strategic Insights

Presented by: Scott Yost

Are you looking to give your students hands-on experience in marketing analytics? Learn how you can use a simulation in your classroom that combines AI and Auto-grading to not only create an exciting analytics course but also save yourself hours of prep time!