Classification in the Wild

Rules for building formal models that use fast-and-frugal heuristics, extending the psychological study of classification to the real world of uncertainty.

This book focuses on classification--allocating objects into categories--"in the wild," in real-world situations and far from the certainty of the lab. In the wild, unlike in typical psychological experiments, the future is not knowable and uncertainty cannot be meaningfully reduced to probability. Connecting the science of heuristics with machine learning, the book shows how to create formal models using classification rules that are simple, fast, and transparent and that can be as accurate as mathematically sophisticated algorithms developed for machine learning.Acknowledgments ix
Introduction: Why Classification in the Wild? 1
1 Four Cases of Classification in the Wild 5
2 Fast-and-Frugal Classification 29
3 Building Fast-and-Frugal Classifiers 51
4 Classification in Machine Learning 79
5 Classification in Cognitive Psychology 109
6 Building a Safer World 129
7 Conclusions 149
Notes 151
Bibliography 171
Author Index 185
Subject Index 191“Is the book engaging and interesting for scientists and practitioners? If no—then don’t buy; if yes, then continue. I think yes, so continue. Does the book provide clear and simple guidelines for building classifiers that work in the wild? If no—then don’t buy; if yes, then continue. I think yes, so continue. Does the book provide tools for analyzing and comparing performance of simple heuristic versus complex machine classifiers? If no—then don’t buy; if yes, then buy. I think yes, so I recommend buy.”
—Jerome Busemeyer, Distinguished Professor, Department of Psychological & Brain Sciences and Cognitive Science Program, Indiana University Bloomington
 
“Practical decision making, in conditions of intrinsic uncertainty, is something every one of us has wrestled with in our jobs and in our everyday lives. This marvelous book by prominent academics drawn from across disciplines, applying their heuristic approaches to a wide range of decision environments, is a timely and thought-provoking step forward in our thinking and practices on this key issue.”
—Andy Haldane, Chief Economist, Bank of EnglandKonstantinos Katsikopoulos is Associate Professor (Reader) of Behavioural Operations at the Southampton Business School, where he is also Head of Research in the Department of Decision Analytics and Risk. Ozgur Simsek is Senior Lecturer in Machine Learning in the Department of Computer Science at the University of Bath, where he is also Deputy Director of the Institute for Mathematical Innovation. Marcus Buckmann is Senior Data Research Analyst at the Advanced Analytics Division of the Bank of England. Gerd Gigerenzer is Director of the Harding Center for Risk Literacy at the Max Planck Institute for Human Development in Berlin and Partner in Simply Rational--The Institute for Decisions.