IBM Decision Optimization for Watson Studio

The solution combines mathematical and artificial intelligence techniques to help make important business decisions that involve multiple decision variables, trade-off possibilities and complex constraints. Integration with IBM Watson® Studio lets you combine optimization and machine learning techniques with model management and deployment capabilities. It helps optimize complex business decisions to help generate significant returns on investments across a wide range of industries.

Data science teams can quickly build and evaluate optimization models in a unified, collaborative environment. The solution can also help configure and evaluate proof-of-concept applications quickly and scale them to production easily by deploying the models within IBM Watson Machine Learning.

IBM Decision Optimization solutions incorporate highly powerful mathematical programming and constraint programming engines to address all classes of business problems across domains. Take advantage of IBM® CPLEX® solvers, which many organizations use to run their mission-critical decision-making applications. IBM CPLEX solvers can help solve large, real-world optimization problems with the speed required for today's interactive decision optimization applications.

Benefit from using the modeling assistant to guide you during the creation of optimization models around scheduling and resource assignment. The modeling assistant uses natural language interactions to define goals and constraints for the model with no coding required. It starts with data input and analyzes the appropriate constraints for the problem that you are trying to address.

IBM Watson Studio offers data scientists a complete set of tools drawn from open source and IBM technologies. It gives data science teams access to peer communities and offers scalability and greater security — making the solution highly adaptable to a broad range of applications. Integration of optimization capabilities within IBM Watson Studio allows teams to quickly scale their proof-of-concept applications and deploy optimization models into production.

Easily create optimization models by coding in Python or using the modeling assistant. Share graphical dashboards with business analysts to validate the benefits of the models. Use powerful visualization features to test multiple scenarios. Deploy the validated model and optimization engine as a microservice, which business users can then access from their applications.