Meta-inductive prediction based on Attractivity Weighting: Mathematical and empirical performance evaluation

Abstract In the present paper, we present mathematical and empirical results concerning the performance of a meta-inductive prediction method known as Attractivity Weighting. The mathematical results show that Attractivity Weighting is endowed with important guarantees concerning its worst-case short run and long run performance. In addition to these guarantees which hold for all logically possible environments, simulations applied to data describing real-world environments suggest that the short run performance of carefully selected forms of Attractivity Weighting is generally very good, both in environments in which one-reason prediction methods are optimal and in environments in which weighting methods are optimal. In both sorts of environment, Attractivity Weighting approximates the performance of that available prediction method that is optimal in that environment.

[1]  Bogdan Gabrys,et al.  Metalearning: a survey of trends and technologies , 2013, Artificial Intelligence Review.

[2]  U. Hoffrage,et al.  Fast, frugal, and fit: Simple heuristics for paired comparison , 2002 .

[3]  J. Rieskamp,et al.  SSL: a theory of how people learn to select strategies. , 2006, Journal of experimental psychology. General.

[4]  Robin M. Hogarth,et al.  Ignoring information in binary choice with continuous variables: When is less “more”? , 2005 .

[5]  Gerd Gigerenzer,et al.  Homo Heuristicus: Why Biased Minds Make Better Inferences , 2009, Top. Cogn. Sci..

[6]  B. Newell,et al.  Empirical tests of a fast-and-frugal heuristic: Not everyone "takes-the-best" , 2003 .

[7]  A. Bröder.  Decision making with the "adaptive toolbox": influence of environmental structure, intelligence, and working memory load. , 2003, Journal of experimental psychology. Learning, memory, and cognition.

[8]  Jörg Rieskamp,et al.  RedundancyEnvironment Structure That Simple Heuristics Can Exploit , 2012 .

[9]  Paul D. Thorn,et al.  The Revenge of Ecological Rationality: Strategy-Selection by Meta-Induction Within Changing Environments , 2015, Minds and Machines.

[10]  A. Bröder,et al.  Adaptive flexibility and maladaptive routines in selecting fast and frugal decision strategies. , 2006, Journal of experimental psychology. Learning, memory, and cognition.

[11]  P. Todd,et al.  The Quest for Take The Best - Insights and Outlooks from Experimental Research , 2011 .

[12]  P. Todd,et al.  Simple Heuristics That Make Us Smart , 1999 .

[13]  J. Rieskamp.  The importance of learning when making inferences , 2008, Judgment and Decision Making.

[14]  Juan A. Carrasco,et al.  Cumulative dominance and heuristic performance in binary multi-attribute choice , 2006 .

[15]  Paul D. Thorn,et al.  Meta-Induction and the Wisdom of Crowds , 2012 .

[16]  Peter M. Todd,et al.  Simple Rules for Ordering Cues in One-Reason Decision Making , 2012 .

[17]  Marc Jekel,et al.  The rationality of different kinds of intuitive decision processes , 2012, Synthese.

[18]  Kathryn B. Laskey,et al.  Bayesian benchmarks for fast and frugal heuristics , 1999 .

[19]  Amnon Rapoport,et al.  Equilibrium Play in Single-Server Queues with Endogenously Determined Arrival Times , 2004 .

[20]  P. Todd,et al.  Ecological Rationality: Intelligence in the World , 2012 .

[21]  R. Selten,et al.  Bounded rationality: The adaptive toolbox , 2000 .

[22]  Sébastien Bubeck,et al.  Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems , 2012, Found. Trends Mach. Learn..

[23]  D. Goldstein,et al.  Betting on one good reason : The Take the Best heuristic , 1999 .

[24]  Gerd Gigerenzer,et al.  How heuristics handle uncertainty , 2012 .

[25]  D. Goldstein,et al.  How good are simple heuristics , 1999 .

[26]  Paul D. Thorn.  Wise Crowds, Clever Meta-Inductivists , 2015 .

[27]  B. Newell,et al.  Take the best or look at the rest? Factors influencing "one-reason" decision making. , 2003, Journal of experimental psychology. Learning, memory, and cognition.

[28]  Gerhard Schurz,et al.  Hume's Problem Solved , 2019 .

[29]  Paul D. Thorn,et al.  Attractivity Weighting: Take-the-Best's Foolproof Sibling , 2016, CogSci.

[30]  Konstantinos V. Katsikopoulos,et al.  Psychological Heuristics for Making Inferences: Definition, Performance, and the Emerging Theory and Practice , 2011, Decis. Anal..

[31]  B. Newell,et al.  Search strategies in decision making: the success of “success” , 2004 .

[32]  Ido Erev,et al.  Equilibrium Play in Large Group Market Entry Games , 1998 .

[33]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[34]  Leah Henderson,et al.  The problem of induction , 2018 .

[35]  Michael Schmitt,et al.  On the Complexity of Learning Lexicographic Strategies , 2006, J. Mach. Learn. Res..

[36]  G Gigerenzer,et al.  Hindsight bias: a by-product of knowledge updating? , 2000, Journal of experimental psychology. Learning, memory, and cognition.

[37]  Ralph Hertwig,et al.  The robust beauty of ordinary information. , 2010, Psychological review.

[38]  Robin M. Hogarth,et al.  "Take-the-best" and other simple strategies: Why and when they work "well" with binary cues , 2006 .

[39]  Gerhard Schurz,et al.  The Meta‐inductivist’s Winning Strategy in the Prediction Game: A New Approach to Hume’s Problem* , 2008, Philosophy of Science.

[40]  Eyran J. Gisches,et al.  Pre-trip Information and Route-Choice Decisions with Stochastic Travel Conditions : Experiment , 2014 .

[41]  Konstantinos V. Katsikopoulos,et al.  Naïve heuristics for paired comparisons: Some results on their relative accuracy , 2006 .

[42]  Ian N. Durbach,et al.  When should we use simple decision models? A synthesis of various research strands , 2017, Omega.

[43]  Gerd Gigerenzer,et al.  Heuristic decision making. , 2011, Annual review of psychology.

[44]  Özgür Simsek,et al.  Linear decision rule as aspiration for simple decision heuristics , 2013, NIPS.

[45]  Marcus Buckmann,et al.  Learning From Small Samples: An Analysis of Simple Decision Heuristics , 2015, NIPS.