Abstract
The concept of optimizing decisions based on predictions considering additional data and constraints introduced in Chapter 1, “AI Introduction,” is often critical to solve real business problems. Decision optimization (DO) takes predictive insight one step further and guarantees that an optimal combination of business-relevant actions can be taken based on predictive insight with relevant context.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See [1] for more information on IBM Watson Studio.
- 2.
We are using IBM Watson Studio for this example; however, similar tools from a variety of different vendors could be used as well.
- 3.
See [2] and [3] for more information on notebooks for data scientists.
- 4.
Correlation discovery is an essential aspect of ML; see [4] for more information on correlation discovery and its applicability in ML.
- 5.
See [5] for more information on Auto AI.
- 6.
See [6] for more information on hyperparameter optimization.
- 7.
See [7] for more information on SPSS.
- 8.
See [8] for more information on DO from Alain Chabrier.
- 9.
See [9] for more information on the docplex engine.
- 10.
More information on how to use docplex in notebooks can be found here: https://github.com/IBMDecisionOptimization/docplex-examples.
- 11.
CI/CD stands for continuous integration and continuous delivery.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2020 Eberhard Hechler, Martin Oberhofer, Thomas Schaeck
About this chapter
Cite this chapter
Hechler, E., Oberhofer, M., Schaeck, T. (2020). From Data to Predictions to Optimal Actions. In: Deploying AI in the Enterprise. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-6206-1_5
Download citation
DOI: https://doi.org/10.1007/978-1-4842-6206-1_5
Published:
Publisher Name: Apress, Berkeley, CA
Print ISBN: 978-1-4842-6205-4
Online ISBN: 978-1-4842-6206-1
eBook Packages: Professional and Applied ComputingApress Access BooksProfessional and Applied Computing (R0)