A Short Introduction to Information-Theoretic Cost-Benefit Analysis
It addresses the need for a measurement tool to explain trade-offs in machine learning, human cognition, and other data intelligence areas, but is incremental as it builds on prior work.
This report introduces an information-theoretic measure for analyzing cost-benefit trade-offs in data intelligence workflows, originally developed in 2016, and notes ongoing efforts to enhance its mathematical properties for practical use.
This arXiv report provides a short introduction to the information-theoretic measure proposed by Chen and Golan in 2016 for analyzing machine- and human-centric processes in data intelligence workflows. This introduction was compiled based on several appendices written to accompany a few research papers on topics of data visualization and visual analytics. Although the original 2016 paper and the follow-on papers were mostly published in the field of visualization and visual analytics, the cost-benefit measure can help explain the informative trade-off in a wide range of data intelligence phenomena including machine learning, human cognition, language development, and so on. Meanwhile, there is an ongoing effort to improve its mathematical properties in order to make it more intuitive and usable in practical applications as a measurement tool.