Outcome Reasoning: the under-discussed engine powering black box development

This is a talk given by Prof Mike Baiocchi as part of the Online Seminar Series Machine Learning NeEDS Mathematical Optimization, https://congreso.us.es/mlneedsmo/, branding the role of Operations Research in Artificial Intelligence with the support of EURO, https://www.euro-     online.org.

Abstract:

For a long time in (bio)statistics we only had two fundamental ways of reasoning using data: warranted reasoning (e.g., randomized trials) and model reasoning (e.g., linear models). In the 1980s a new, extraordinarily productive way of reasoning about algorithms emerged: «outcome reasoning.» Outcome reasoning has come to dominate areas of data science, it has been under-discussed and its impact under-appreciated. For example, it is the primary way we reason about «black box» algorithms. In this talk we will discuss its current use (i.e., as «the common task framework») and its limitations. I will show why we find a large class of prediction-problems are inappropriate for this new type of reasoning. I will then discuss a way to extend this type of reasoning for use, where appropriate, in assessing algorithms for deployment (i.e., when using a predictive algorithm «in the real world»). We purposefully developed this new framework so both technical and non-technical people can discuss and identify key features of their prediction problem.

More information

Link to the talk: https://eu.bbcollab.com/guest/c8ae1469ed034fddb17cddcde67972ac

Organisers

The organizers of the Online Seminar Series Machine Learning NeEDS Mathematical Optimization
Emilio Carrizosa, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Nuria Gómez-Vargas, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Thomas Halskov, Copenhagen Business School
Dolores Romero Morales, Copenhagen Business School