Take advantage of in-depth training in software solutions provided by leading analytics companies. There is no charge for these workshops if you register for the INFORMS Annual Meeting. All workshops take place on Saturday, November 8th, at the Hilton San Francisco Union Square.
Sign up for any of these workshops when you register for the meeting. If you have already registered, call 800.446.3676 or 443.757.3500 to add workshops.
9:00am - 11:30am
12:00pm - 2:30pm
|3:00pm - 5:30pm|
|Imagine That Inc.|
Non-profit ProbabilityManagement.org promotes standards for communicating uncertainties through arrays of big data known as SIPs (Stochastic Information Packets). Topics: • the origins of Probability Management • the open SIPmath™ Standard • interactive simulation in Excel without macros or add-ins using the Data Table • SIPmath Modeler Tools for facilitating the generation of such models • aggregating uncertainty across the enterprise • applications - energy - defense - finance - in the classroom • leveraging Crystal Ball, @Risk, Risk Solver, Matlab, R and SAS • harvesting probability distributions from such sources as the Federal Reserve, and US Geological Survey. Visit SIPmath.org for videos and Excel demo models.
Using AIMMS PRO to Solve Large and Complex Optimization Models
Is the mathematical model you are trying to solve becoming too complex? Do you need more computational power to find a feasible solution in a timely manner? Come and see how AIMMS PRO can be used to build and deliver highly complex math programs as web-based optimization solutions. In the workshop, we will address the complexity of several business problems and show the various features of AIMMS PRO that facilitated a rapid, smooth, robust, and integrated solution and implementation. Presenters: Deanne Zhang, Sr. AIMMS Optimization Specialist; Bobby Nyotta, AIMMS Optimization Specialist.
Nonlinear Optimization Package Focusing on Stochastic Applications
Portfolio Safeguard is an advanced nonlinear mixed-integer optimization package used in risk management, financial engineering, military, medical and other applications. Design and solve complex optimization problems with built-in functions (linear, quadratic, maximum, StDev, variance, probability, VaR, CVaR, cardinality, fixed-charge, etc.). See real-life case studies in Windows and MATLAB at www.aorda.com/aod/psg.action, including: portfolio hedging - calibrating probabilistic distributions (Copulas) with relative entropy - portfolio optimization with CVaR, VaR, drawdown constraints - structuring collateralized obligations with probability (rating) constraints - quantile regression - logistics with uncertain environment (e.g., optimal crop production) - bond portfolio cash matching - optimizing radiation therapy.
When evaluating choices significant effort is placed on analytics. Scoring, producing a model and carrying out sensitivity analysis are all aspects that are familiar. However, what if the choices being evaluated aren't the right ones or incomplete? Even the most sophisticated analytics will not help. Typically, only rudimentary brainstorming is used to generate the options. We will be exploring some structured methods that are a significant improvement on the traditional approach.
Turnkey Optimization on the Cloud
We will demonstrate enhancements in the linear, mixed integer and nonlinear solvers in the latest release of the FICO® Xpress Optimization Suite version 7.8, including a groundbreaking innovation for simplex algorithms. In addition, we will introduce robust modeling and optimization capabilities in Xpress and demonstrate the ease of modeling complex problems. We will discuss how to deploy optimization applications on the FICO® Analytic Cloud. Through the FICO® Decision Management Platform, FICO’s new cloud-based tools platform, you can build, implement and scale complex solutions combining predictive analytics, rules and optimization.
Gurobi Optimizer Recent Release
The workshop will talk about our most recent Gurobi Optimizer release, which contains both performance improvements and several new features. One important new feature is algorithmic support for piecewise-linear objective functions. By moving this into the simplex algorithm, we allow users to create much more accurate approximations of non-linear functions without incurring a significant performance penalty. Another important feature is our new distributed MIP solver, which provides higher performance by employing multiple machines on a single solve. The workshop will include usage examples and performance results for each of these exciting new capabilities.
Play Online Games for Operations Management and Supply Chain Courses
This workshop will be split into two 45-minute sessions where participants will play abbreviated versions of online games used in hundreds of institutions worldwide to engage students in traditional Operations courses. One session will cover Littlefield Technologies and the other will cover the ebeer game. Participants are encouraged to bring a laptop but not required to do so.
Solving Business Problems with SAS Analytics and OPTMODEL
SAS provides diverse analytic capabilities, including data integration, statistical analysis, data/text mining, and forecasting, all integrated with OPTMODEL’s optimization modeling and solution capabilities. OPTMODEL provides unified support for LP, MILP, QP, NLP, CLP, and network-oriented models and methods, including an expanding suite of standard solvers and support for customized algorithms. We’ll demonstrate OPTMODEL’s power and versatility in building and solving optimization models, noting the significant improvements resulting from new and upcoming features. We’ll emphasize integration with SAS data, analytic, and reporting capabilities, focusing primarily on case studies drawn from our successful work with customers across a broad range of industries.
Using SAS Visual Analytics
The tutorial will demo SAS Visual Analytics to show you that you can explore all relevant data quickly and easily. You can look at more options, uncover hidden opportunities, identify key relationships and make more precise decisions faster than ever before. Self-service, ad hoc visual data discovery and exploration put lightning-fast insights within everyone's reach. Presenters are Mike Speed and Tom Bohannon.
JMP®: Interactive and Visual Data Analysis with JMP 11 Pro
JMP®, developed by SAS Institute, is dynamic and interactive desktop software for data analysis, visualization and modeling. We’ll demonstrate JMP tools for interactive exploratory data analysis and statistical modeling. We’ll build logistic and least squares regression models with stepwise regression, generalized regression, develop classification and regression trees, and build flexible neural networks. We’ll explore bootstrapped forests and boosted trees, illustrate methods for model validation, and visualize results using the Graph Builder®, Data Filter, and the Prediction Profiler. Finally, we’ll compare competing models using JMP Pro’s Model Comparison. Workshop presented by Darryl Revenew, JMP Academic Ambassador.
ANYLOGIC 7 - Faster, Simpler Model Building with Improved Capabilities
AnyLogic 7, the newest version of the most definitive simulation and modeling software available has been released. Features include: true integration of modeling methods • all active objects are agents • entity = resource unit = agent space markup • nodes, paths, walls, services, rail tracks, pallet racks • unified space for all objects new discrete-event process modeling library • “pull” entity flow • flexible resource management: alternative sets, preparation and wrap-up, shifts, breaks • “internals” of entities defined graphically improved Pedestrian Library • performance • ease of use, space markup rail library enhancements • rail network construction • collection of US rail car 3D model.
Artelys Crystal Super Grid, a Power Systems Modeling Software for Cost-Benefit Analysis of Energy Projects
This presentation focuses on the use of Artelys Crystal Super Grid, a power systems modeling software developed by Artelys. Our users are investors, regulation authorities and independent system operators (ISO), ministries, consultants or transmission system operators (TSO/RTO). Their objective is to evaluate in detail the interest of specific projects (generation/transmission/storage) in terms of revenue, social welfare, pollutant emissions, and security of supply in a region. To this purpose, Artelys Crystal Super Grid uses built-in libraries of power assets and indicators, along with a powerful optimization engine, to simulate systems with tens of interconnected regions on an hourly basis. Its intuitive interface allows for efficient analysis, comparison and evaluation of large number of scenarios. Presenter: Guillaume Tarel, PhD, VP Artelys Canada.
Creating and Publishing Interactive Online Analytics Applications
Learn how to get your analytics, machine learning, or OR application running on the web in a free Forio account. If you don’t have a model with you, you can use a sample model to produce an interactive web application. We will start with an introduction to the Forio platform. In the first part we will help you get your model or optimization running on Forio’s servers. We’ll walk through the process of importing your model to the server. In the second half we’ll focus on creating an interactive user interface for your application. After the introduction, you will be able to work on your own. Forio will also provide a debrief on online analytics applications and suggest possible next steps for enhancing your own online tool. Bring a laptop if you would like to participate.
Analytics Made Easy: Data Mining, Simulation and Optimization for Excel and the Web
Discover the easiest, fastest, lowest cost and risk "on ramp" to full-power predictive and prescriptive analytics, from Excel Solver developer Frontline Systems, the company that's democratizing analytics. We’ll demonstrate our new, “hot” Risk Solver, Premium Solver, and XLMiner Apps for Excel Online in Office 365, and give “sneak previews” of major enhancements in Analytic Solver Platform V2015 and Solver Server V2015. You’ll see how our integrated toolset can meet your needs for forecasting and sophisticated data mining, Monte Carlo simulation and risk analysis, and conventional and stochastic optimization – without the complexity and high cost of "enterprise" solutions.
An Introduction to Model Development with GAMS
In this workshop we start with the basics of using GAMS to develop algebraic models and solve them using state-of-the art solvers. We'll introduce the fundamentals (e.g. sets, data, variables, equations) using simple LP models, and show how GAMS supports an easy growth path to larger and more sophisticated models (e.g. NLP, MIP). Along the way we'll look at some of the data management tools included in the GAMS system and give an overview of the many useful capabilities found in the GAMS IDE. We'll conclude with an example application showing how all of these things can be integrated and deployed as part of a larger application. Presenter is Steve Dirkse, Director of Optimization.
Analytics in the Cloud: Predictive, Prescriptive, Cognitive
Learn the latest innovations from IBM in Predictive, Prescriptive, and Cognitive Analytics that enable decision-making at the speed of business with the flexibility of the cloud. We’ll share how IBM’s Analytics portfolio helps businesses gain a unique competitive advantage from the powerful tools of Advanced Analytics. Get access to deep technical content and learn best practices from optimization and analytics expert to apply optimization and advanced analytic technologies in new ways.
|3:00-3:30pm||IBM Watson Analytics-Harnessing the power of Descriptive and Predictive Analytics through Cognitive Computing|
|3:45-4:15pm||Innovations in IBM Decision Optimization that Bridge the Gap Between Data and Decision-Making|
|4:45-5:15pm||Solving Large Scale Optimization Problems using CPLEX Optimization Studio, Dr. Robert Ashford, Optimization Direct, Inc.|
Solutions Through Simulation with ExtendSim
Simulation is a key technology to understanding your organization’s processes and identifying opportunities for improvement. Using the ExtendSim simulation program will give you insight into your data, simplifying complex problems into an understandable and intuitive format transforming your data into information. ExtendSim models are engaging and easy to experiment with so you can glean actionable insights to make the right decision. This workshop will include an ExtendSim model building session and demonstrate a range of real world models from a variety of industries. Experience the ease at which robust, intuitive models are built with the power tool for simulation - ExtendSim.
Faster, Easier, More Powerful: See the New Releases in LINDO Software
The latest versions of our optimizers, What’sBest!, LINGO and the LINDO API have both notable performance improvements and some impressive new functionalities. You can now effortlessly solve large optimization problems of all varieties: linear, integer, quadratic, conic, semi-definite, nonlinear, global and stochastic. And of course, the ease-of-use that has been the hallmark of LINDO is better than ever. Leave with full-featured trial versions of our products and the knowledge you need to jump-start your next project.
What’s new in MATLAB for Analytics and Optimization?
MATLAB is a platform for analysis, visualization, simulation, and optimization. In this workshop, you’ll learn about new developments in MATLAB for exploring and visualizing data, developing algorithms, and integrating with enterprise applications. You’ll see how MATLAB makes it easy to scale up your analysis from in-memory calculations to working with big data. We’ll discuss new MATLAB features including mixed-integer linear programming and machine learning. Finally, you’ll learn about the various options for deploying your MATLAB code, such as creating standalone executables and integrating your analytics with enterprise applications.
Review of Analytics Methods
The Wall Street Journal terms “data science” the “hottest career of the tech job market.” This workshop will review statistical and data mining methods that are part of the data science mix: predictive modeling, visualization, customer segmentation, collaborative filtering, data reduction, and more. The presentation is a survey of various methods and their vocabulary, and will draw on the vendor-neutral training at Statistics.com, where hands-on software experience is stressed. It will focus on what various methods do and the business context in which they operate, rather than the algorithm details and statistical properties of the methods. Presented by Peter Bruce, President.