IBM® Decision Optimization for Watson Studio enables data science teams to capitalize on the power of prescriptive analytics and build solutions using a combination of techniques like machine learning and optimization. It is integrated with IBM® Watson Studio that combines optimization techniques with coding and non-coding tools, model management and deployment – as well as other data science capabilities. The solution evaluates millions of possibilities – balancing trade-offs and business constraints to find the best possible solution.

Deliver Business Results by Combining Optimization and Machine Learning

5 minute demo

In this video you can explore the benefits and use cases of combining machine learning techniques with decision optimization to deliver business results.

Deliver Optimal Business Decisions with IBM Data Science Experience

4 minute demo

Learn how IBM Decision Optimization for Data Science Experience provides the capabilities to combine optimization techniques with other data science capabilities to help deliver business impact.

IBM Decision Optimization in Action on Data Science Experience

8 minute demo

This video demonstrates the capabilities of IBM Decision Optimization for Data Science Experience that enables data science teams to capitalize on the power of prescriptive analytics and build solutions using a combination of techniques like machine learning and optimization.

Introduction to Decision Optimization for Data Science Experience

9 minute demo

Learn the value and capabilities of Decision Optimization and walk through a typical data science application to learn how it uses machine learning and optimization models. See how data scientists can easily combine both of these approaches to develop and deploy models.

Tour IBM Decision Optimization for Watson Studio: Create and deploy an optimization model

Build and deploy an optimization model like an expert with IBM® Decision Optimization for Watson Studio.

  • Create an optimization project and load a data set
  • Start to develop an optimization model and prepare the data set
  • Finish the development of the optimization model by using the modeling assistant
  • Solve the optimization model and review the results
  • Create a dashboard for the results
  • Experiment with different scenarios
  • Prepare the model for deployment

15-30 minute introduction