Skip to content

Technology Tutorials


Monday April 16, 3:40-4:30pm

AMPL in the Cloud:
Using Online Services to Develop and Deploy Optimization Applications through Algebraic Modeling
Presented by: Robert Fourer, Filipe Brandão, Martin Laskowski
AMPL Optimization Inc.

Cloud services promising “optimization on demand” have become steadily more numerous and more powerful in recent years. This presentation offers a user-oriented survey, with a focus on the role of the AMPL modeling language in streamlining development and deployment of optimization models using online tools. Starting with the pioneering free NEOS Server, we compare more recent commercial offerings such as Gurobi Instant Cloud and the Satalia SolveEngine; the benefits of these solver services are enhanced through their use with AMPL’s algebraic modeling facilities. We conclude by introducing QuanDec, which turns AMPL models into web-based collaborative decision-making tools.

AnyLogic Company

Monday April 16, 9:10-10am

anyLogistix Supply Chain Software: New Features and Roadmap
Presented by: Timofey Popkov, Director of Business Development & Dr. Robert de Souza, Executive Director

anyLogistix software will help your organization to optimize, design and experiment with your supply chains. It combines analytical optimization together with unmatched simulation technology enabling precise end-to-end supply chain analysis.  In a risk free space, you may test new ideas to see how your innovations with your supply chain will work in the real world.  During the workshop you will learn how to develop models in anyLogistix and discover ways you may benefit by utilizing multiple approaches with your supply chain design.

Artelys Corp. 

Monday April 16, 10:30-11:20am

Introducing the New API and Conic Solver in Artelys Knitro 11.0
Presented by: Richard Waltz, Senior Scientist, Artelys Corp,

Artelys Knitro is the premier solver for nonlinear optimization problems. This software demonstration will highlight two key features in the new, major Knitro 11.0 release.  First, we will demonstrate the new callable library API.  This new API allows the user to build-up a model in pieces while providing special structures to Knitro.  Second, we will introduce the new solver in Knitro 11.0 specially designed for models with cone constraints.  Some benchmarking results will be provided.

Artelys Corp. 

Monday April 16, 1:50-2:40pm

Optimizing Hydropower Generation
Presented by: Violette Berge, Vice President at Artelys Canada Inc 

Artelys will present the Artelys Crystal software solution, which is devoted to the modelling and optimization of energy systems, and in particular of hydropower plants. Fully customizable, this solution enables hydropower producers to realistically model their generation resources, taking into account all specific operational and market-related constraints. Thanks to its state-of-the-art combinatorial optimization techniques, the software takes advantage of all the sources of flexibility to automatically generate reliable least cost schedules. The ergonomic user-interface is designed to ease input data, visualize production plans and export them.

Booz Allen Hamilton

Tuesday April 17, 10:30-11:20am

Bring Your Analytics and Simulation to your Fingertips through Open Source
Presented by: Patrick McCreesh – Principal/Director, Chris Brown – Chief Technologist, Ryan Haughey – Lead Scientist & Tyler Buffum – Lead Scientist

Open source solutions drive data management, the ETL process, analytics, and automation that drive the development of insights that improve decision making. This tutorial will enable you to lead and be the change through deep understanding of the depth and breadth of relevant open source applications to build or enhance your data lake, develop meaningful visualizations, create robust simulations, and scale machine learning.


Monday April 16, 1:50-2:40pm

How to deploy your ML and optimization models to empower non-technical business users
Presented by: Jim Williams

You have a team with a great analytics background. They have developed advanced analytical tools using Python, R, or with your current traditional optimization solver. They have derived crucial insights from your data, and they’ve figured out how your decisions shape your customers’ behaviors. 

Now it’s time to put these critical analytical insights in the hands of your non-technical business users.

In this tutorial, we will cover how FICO’s Optimization Suite (including Xpress-Mosel, Xpress-Workbench, and Xpress-Insight) make it possible to embed your analytic models in business user-friendly applications. Learn how you can supercharge your analytic models with simulation, optimization, reporting, what-if analysis, and agile extensibility.

Frontline Systems, Inc

Tuesday April 17, 11:30am-12:20pm

Keep it Simple: Getting Analytics Results with Less Cost, Time and Risk
Presented by: Daniel Fylstra, President, Frontline Systems Inc.

Many organizations today are trying to invest in analytics, hire data scientists, deal with “big data”, and get results. Some roads ahead involve big commitments, high costs, and complexity.  But another road is possible:  Start small, keep it simple, and recognize you have more in-house expertise than you thought.  This session will show how you can use skills you have and tools like Excel and C# to build optimization, simulation, and data mining applications; Tableau and Power BI to connect models to data (even “big data”) and deploy them widely; and resources like Solver. Academy to build your team’s expertise.


Tuesday April 17, 1:50-2:40pm

Enhanced Model Deployment and Solution in GAMS
Presented by: Steve Dirkse, President, GAMS Development

In most cases, using GAMS in the typical fashion – i.e. defining data, variables, equations and models in a declarative way and solving the models sequentially – presents no performance issues.  In some cases, though (e.g. when analyzing multiple scenarios or when implementing a decomposition scheme), performance can be dramatically improved using newer GAMS capabilities. In this tutorial, we’ll first look briefly at the basic features of GAMS and how they are used to build an application using multiple models and (sequential) solves.  We’ll build on that by showing different techniques to implement the same application using parallel solves on a typical desktop computer or on a high-performance computational cluster.

Gurobi Optimization

Monday April 16, 11:30am-12:20pm

Gurobi Compute Server and Instant Cloud
Presented by: Dr. Michel Jaczynski, Sr. Software Architect, Gurobi Optimization

Gurobi Compute Server is designed to greatly simplify the task of building and deploying modern optimization applications, by allowing you to seamlessly offload your optimization computations onto a set of one or more dedicated optimization servers. You can deploy Compute Server on your own, in-house servers, or on the cloud using Gurobi Instant Cloud. This presentation will present several new Compute Server and Instant Cloud features. We’ll discuss different usage scenarios, and give a demo of the new features.


Monday April 16, 9:10-10am

Automatic Benders Decomposition in CPLEX
Presented by: Ed Klotz

Benders Decomposition has been used in practice for many years to solve certain types of linear and integer programs that are very challenging for the simplex, barrier and branch-and-bound algorithms. CPLEX’s APIs have always been very well suited for the problem modifications and interactions between problems needed to implement Benders or other decomposition methods. However, such implementations typically require significant knowledge of the details of Benders decomposition for the development
and debugging process. By contrast, the automatic Benders Decomposition algorithm available starting with version 12.7 of CPLEX can be used with little, if any, knowledge about the algorithm. This presentation will discuss how to effectively use this new feature, and how to recognize when it is likely to perform well on linear or mixed integer programs that otherwise might be difficult to solve.

Tuesday April 17, 4:40-5:30pm

Retail-as-a-Service from JD.COM
Presented by: Zuo-Jun Max Shen

Technology, especially the rapid adoption of mobile technology, has completely transformed the traditional retail landscape. As China’s largest retailer online or offline, leverages technology and AI to develop cutting-edge retail solutions that enable more personalized marketing and a more efficient supply chain management system, all aimed at improving the customer experience.

Guided by a “Retail as a Service” (RaaS) vision the company is focused on how to use its advantages to enable its partners and suppliers to achieve new heights. Data Science (DS) and Operations Research (OR) are among the core techniques supporting JD’s RaaS strategy. In this tutorial, we will provide an overview of current best practice and highlight the key contributions that DS and OR have made in realizing RaaS. We will introduce key initiatives from that enable us to offer an innovative retail experience to both customers and supply chain partners and demonstrate how these technologies have improved the shopping experience and operational efficiency for both online and offline retailers.

Lindo Systems, Inc

Monday April 16, 11:30am-12:20pm

Optimization Modeling Tools from LINDO Systems
Presented by: Mark Wiley

Exceptional ease of use, widest 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 a full range of 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 all the tools you need to get up and running quickly. LINDO provides a set of versatile intuitive interfaces to suit your modeling preference.

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

You can 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 guidance on handling a particular application. Get started today. Visit our booth or to get more information and pick up full capacity evaluation licenses to try them out on your toughest models.


Tuesday April 17, 9:10-10am

Predictive and Prescriptive Analytics with MATLAB
Presented by: Mary Fenelon

MATLAB makes it easy to build applications that include both predictive and prescriptive analytics.  In this tutorial you will learn how to access data from the web, preprocess it, experiment with machine learning models, and formulate optimization problems using the new, simplified modeling tools in MATLAB. We will show these steps by building an app that predicts electrical power system demand and prescribes an optimal generator schedule to satisfy that demand.

Optimization Direct

Monday April 16, 9:10-10am

A DOCplex and ODH|CPLEX python primer
Presented by: Joshua Woodruff & Robert Ashford

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. 

The Optimization Firm

Monday April 16, 3:40-4:30

ALAMO: Machine learning from data and first principles
Presented by: Nick Sahinidis, The Optimization Firm,,

Got data?  Then you’ll love ALAMO.  The ALAMO tool is groundbreaking machine learning software that utilizes data and first principles.  It takes data from experiments and simulations and generates models that are accurate and simple at the same time.

This tutorial is designed for people interested in the construction of mathematical models using data.  The presentation will highlight ALAMO’s framework and features, including a spreadsheet-based GUI, simple command-line interface, powerful embedded optimization technology, and insightful graphical representations of data and results.

The software demonstration will show how ALAMO can:

  • use a preexisting dataset to build low-complexity models
  • guide the collection of data points to build or improve models
  • enforce physical constraints on the mathematical structure of the model
  • address a number of challenging machine learning problems.

By the end of this tutorial, attendees will have enough background and demonstrations to make it possible to easily generate interpretable models from data.

Princeton Consultants, Inc

Monday April 16, 1:50-2:40pm

Optimization-Simulation: How to Test Models Without Disrupting Operations
Presented by: Dr. Patricia Randall, Director, Princeton Consultants

Many optimization solutions under development require testing in a realistic, dynamic environment–but doing so would disrupt operations. In this tutorial, Dr. Patricia Randall explains that simulation is a viable, robust testing platform for operational software with complex dependencies or for software that would be too time-consuming or costly to test in the field. Simulation is commonly used to answer critical operational and strategic questions by making predictions about the behavior of a system under certain conditions. Its capability to easily model the interaction between entities and incorporate various sources of uncertainty also makes it a powerful testing tool for advanced analytics practitioners. Highlighting a current example at a leading transportation company, Dr. Randall will discuss the basics of simulation software, benefits for using it to test optimization solutions, and tips to get started.

Princeton Consultants, Inc

Tuesday April 17, 9:10-10am

Analytics Model Review and Validation
Presented by: Dr. Irv Lustig, Optimization Principal, Princeton Consultants

Acting as an independent third party, Princeton Consultants reviews analytics models and how they are deployed in a business. Through our Advanced Analytics Model Review and Validation service, we ask questions such as: What is a correct model? What data is being integrated and how? How are solutions published and used in the business? How sensitive are the answers to the inputs? Did the implemented model reflect the intentions of the practitioner? In this tutorial, Irv  Lustig will illustrate the importance of addressing these questions in the context of deploying advanced analytics models in practice.

Provalis Research

Monday April 16, 11:30am-12:20pm

Learn How to Perform Text Mining in Business Analytics
Presented by: Adam Bendriss Alami 

Business Analytics and Operations Research involves researching incident reports, corporate reports, social media, customer reviews and much more. The volume of available text has exploded in the digital age. It is extremely time consuming, expensive and in many cases impossible to read each and every document related to one’s research.  Text Analytics makes it possible to quickly import and analyze very large volumes of text documents. This presentation will showcase the different text analytics approaches used for Business Analytics such as computer assisted qualitative coding; exploratory text mining; content analysis dictionaries or taxonomies, supervised and unsupervised machine learning. We will discuss when one technique may be more appropriate than another and how they can work together to analyze text data.

Purdue University, Krannert School of Management

Tuesday April 17, 4:40-5:30pm

Predictive Model Prototyping with the R caret Package
Presented by: Matthew A. Lanham, Purdue University, Department of Management

This workshop provides an exhaustive deep dive of the available functions and typical order you would use them when prototyping a predictive modeling solution using the R caret package. The motivation for this workshop is that after Max Kuhn provided this wonderful modeling package to the analytical community in 2007, its used has grown dramatically among analytics professionals and data scientists. For the newbie wanting to get up to speed in how to use it, this workshop provides an end-to-end case that demonstrates the functions, reason for their use, and typical order in how you would use them. R code and humor will be provided.

BIO: Matthew is a Clinical Assistant Professor at Purdue Universities’ Krannert School of Management and Co-Founder/Chief Data Scientist of Biz Analytics Lab, LLC in Lafayette, IN. He practices and teaches Data Mining, Predictive Analytics, and Using R for Analytics courses within Krannert, and spends most of his time obtaining and mentoring experimental learning projects for students within Purdue’s M.S. in Business Analytics & Information Management (BAIM) program.


Monday April 16, 10:30-11:20am

Building and Solving Optimization Models with SAS
Presented by: Rob Pratt, Senior R&D Manager and Ed Hughes, Principal Product Manager

SAS provides comprehensive data and analytic capabilities, including statistics, data/text mining, forecasting, and operations research methods: optimization, simulation, and 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, 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®.

SAS Education Practice

Tuesday April 17, 1:50-2:40pm

Is Dash boarding Enough? Exploration is the Future of Big Data and Business Intelligence.
Presented by: James Harroun, Senior Analytical Training Consultant

Data visualization tools have revolutionized the accessibility and availability of organizational knowledge. Compelling visualizations deliver objective recommendations and drive organizational decision-making in efficient and effective ways, but simply visualizing the typical KPI’s and relying on the usual analyses might not allow organizations to challenge their expectations and drive meaningful change through data discovery and exploration. Organizations can dive deep into big data and benefit from the flexibility of collaborative, high-performance, big data analytical tools that synthesize big data exploration and deeper analyses with standard reporting and dashboarding. SAS® Visual Analytics integrates big data analytical muscle into accessible and engaging visualizations that answer questions organizations already need to know and that drive the desire to explore big data, to challenge assumptions, and to democratize analytics.

JMP, a Division of SAS
Monday April 16, 3:40-4:30pm

JMP Pro, and the Analytics Workflow
Presented by: Mia Stephens, Principal Systems Engineer

JMP Statistical Discovery Software from SAS brings interactive data visualization, analysis and modeling to the desktop (Mac or Windows). JMP Pro, the Professional version of JMP, has many tools to facilitate fitting, validation, comparison, and selection of predictive models. In this workshop we use a case study to illustrate the analytics workflow. We’ll compile data, prepare the data for modeling, explore the data, and generate geographic maps and other rich visualizations.  Then, we’ll create a number of predictive models, including multiple linear regression, regression tree, bootstrap (random) forest and boosted tree, neural net, LASSO, and Elastic Net.  We’ll publish models to the Formula Depot, and explore and select the best model(s) using the Prediction Profiler and Model Comparison. Then, we’ll generate scoring code to support the creation of web applications that can calculate housing prices “on the spot.”

Simio Simulation and Scheduling Software

Tuesday April 17, 11:30-12:20pm

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.


Tuesday April 17, 10:30-11:20am

16 Tips for Teaching a Marketing Analytics Course
Presented by: Spencer Halford, Course Consultant

This presentation consists of 16 helpful tips that analytics professors can use to enhance the learning experience in their classrooms. These tips include helpful resources to give to students, as well as key concepts to focus on in an analytics’ course.


Monday April 16, 10:30-11:20am

Why Data Science Projects Fail to Activate
Presented by: Todd Jones – SVP, Analytics

A recent study shows that 25% of data science projects never reach activation with business decision makers. Large investments in advanced analytics and strategic priorities in data-driven decision making will quickly dampen the hype around data science if activation continues to fall below 75%. This presentation explores the relationship between data science teams and business stakeholders, data science development processes extending beyond simply model development, and technology and data architectures that either accelerate or limit operationalizing insights. Explore this walkthrough of specific examples of successful and unsuccessful data science projects to highlight the critical strategies and tactics influencing business change. Join us in discussing how activation, not insights, should be the focal point of any data science project.