Mathematical Optimization: Bringing Better Decisions to Data Science

Why Mixed-Integer Programming is important to data scientists?

Simply put – Mixed-Integer Programming (MIP) answers questions that Machine Learning (ML) cannot.  Incorporating MIP into your data science repertoire opens many more applications up to you and increases your impact on the business.  The techniques of MIP were invented many years ago (also true of ML), but recent advances in computing power, algorithms, and data availability have made it possible to handle the world’s most complex business problems at speed (also true of ML).  As a result, MIP has had a massive impact on a wide variety of business areas (also true of ML).  Analytics without MIP is like a toolbox without a screwdriver. 

How does it work in concert with machine learning techniques?

ML makes predictions while MIP makes decisions. When your problem involves complex tradeoffs between competing activities and allows for trillions of possible solutions, only MIP has the power to find the best or optimal one. MIP is often complementary to ML. For example, instead of using just ML to decide which offer goes in front of which web customer, you can marry ML to MIP to choose a set of offers that drives the greatest profitability. Or consider predictive maintenance (e.g., elevator repair). ML can predict when certain types of failures are likely to occur, and MIP can then allocate and schedule the resources required to perform the needed maintenance at minimum cost.

How can I get started?

The Gurobi Optimization website has case studies, whitepapers, modeling examples, instructional videos and Optimization Application Demos to introduce you to MIP and help you get started. Visit www.gurobi.com and select ‘I am a Data Scientist.’

How hard is it to learn to build an optimization model? It is harder than simple ML techniques like regression and classification, but easier than more advanced techniques like deep learning and reinforcement learning. MIP requires some programming skills and good math background. Visit our website to learn more.

Adding Optimization to Your Data Science Analytics Toolbox

Watch this webinar to see real-world examples of Machine Learning and optimization in action, illustrating the value it can bring to your organization. It also provides you with the next steps on how to get started with optimization as well as available resources.

Data Science Central Podcast with Gurobi

Listen to this podcast to discover how machine learning and optimization can complement each other; the former making predictions about likely future business outcomes, and the latter suggesting appropriate actions to take in order to take advantage of these outcomes.

How Mathematical Optimization Complements Machine Learning

How can you enhance the business decision making process with the use of mathematical optimization and machine learning? Learn more in this video.