Webinar – Learn How to Design and Deploy Optimization Applications

Data Science Webinar Series - Session 3

Go to Session 1

Go to Session 2

Interested in learning how to build and deploy modern optimization applications that deliver tremendous business value?

In this webinar, you will have the opportunity to see several live Gurobi optimization application demos. These demos will showcase the power of mathematical optimization applications and demonstrate how you can deploy these applications on modern IT architectures like Amazon Web Services and Docker.

During the session – which will cover well-known optimization problems such as the facility location problem and workforce scheduling – we will give you an in-depth look at the user interface, the architecture, and the deployment of optimization applications.

The webinar will:

  • Illustrate the business value of optimization.
  • Demonstrate how to interact with an optimization application.
  • Show how this application can be implemented within a modern IT architecture.
  • Go over best practices in deploying your own optimization applications.


Richard Oberdieck, Technical Account Manager at Gurobi. Oberdiek obtained his BSc and MSc degrees from ETH Zurich in Switzerland (2009-2013), before pursuing a Ph.D. in Chemical Engineering at Imperial College London, UK, which he completed in 2017. He published 1 book, 21 papers and 2 book chapters, has an h-index of 11 and was awarded the FICO Decisions Award 2019 in Optimization, Machine Learning and AI. Richard is now helping companies around the world unlock business value through mathematical optimization as a Technical Account Manager for Gurobi Optimization, LLC.

Hosted by:

Sean Welch, Host and Producer – Data Science Central

View the RecordingDownload the Slides


Session 2: Create Mathematical Optimization Models with Python

As part of our 2020 Data Science Webinar Track, we will be hosting the second session in our webinar series developed to instruct Data Scientists on how to use mathematical optimization.

With mathematical optimization, companies can capture the key features of their business problems in an optimization model and can generate optimal solutions (which are used as the basis to make optimal decisions). Data scientists with some basic mathematical programming skills can easily learn how to build, implement, and maintain mathematical optimization applications.

The Gurobi Python API borrows ideas from modeling languages, enabling users to deploy and solve mathematical optimization models with scripts that are easy to write, read, and maintain. Such modules can even be embedded in decision support systems for production-ready applications.

In this webinar, we will:

  • Discuss the motivation for using Python in mathematical optimization applications
  • Help you understand the importance of parameterizing a mathematical optimization model
  • Review some of the best practices for deploying mathematical optimization models in Python


Juan Antonio Orozco Guzman

Juan Antonio Orozco, Optimization Support Engineer at Gurobi  Optimization. Before joining Gurobi, Juan spent several years in the IT industry, performing roles in R&D, business intelligence, and data science. He has also taught undergraduate courses about statistical process control and mathematical optimization in the industrial engineering department at ITESM, campus Guadalajara. Juan earned a M.Sc. in statistics and operational research at the University of Edinburgh with distinction. His main interests are in optimization, machine learning, and deep learning.

Hosted by:

Sean Welch, Host and Producer – Data Science Central

View the Recording


Session 1: Mathematical Optimization Modeling – Learn the Basics

As part of our 2020 Data Science Webinar Track, we hosted the first session in our webinar series developed to instruct Data Scientists on how to use mathematical optimization.

Mathematical optimization (MO) technologies are being utilized today by leading global companies across industries – including aviation, energy, finance, logistics, telecommunications, manufacturing, media, and many more – to solve a wide range of complex, real-world problems, make optimal, data-driven decisions, and achieve greater operational efficiency.

An increasing number of data scientists are adding MO into their analytics toolbox and developing applications that combine MO and machine learning (ML) technologies. In this series of webinars, we will show you how – with MO techniques – you can build interpretable models to tackle your prediction and classification problems.

In this webinar, you will learn:

  • The main components of an MO problem.
  • How to formulate an MO model.
  • How to build an MO model using the Gurobi Python API.
  • How to modify the original model formulation to accommodate changing conditions.
  • How to implement changes in the model using the Gurobi Python API.


Pano Santos, Senior PhD, Senior Technical Manager at Gurobi Optimization. Santos retired from Hewlett-Packard Enterprise as Distinguished Technologist. During his 23 years at HP Labs, he developed and implemented several decision support tools of mathematical programming applications for workforce planning at the services industry, supply chain planning, CRM, transportation and logistics, and operating room Scheduling. Santos has a Bachelor’s degree in applied mathematics from the University of Mexico (UNAM), and a Master and PhD degrees in Operations Research from the University of Waterloo in Canada.

Hosted by:

Sean Welch, Host and Producer – Data Science Central

View the Recording


Learn How to Design and Deploy Optimization Applications