Predicting human decisions with behavioral theories and machine learning

Behavioral decision theories aim to explain human behavior. Can they help predict it? An open tournament for prediction of human choices in fundamental economic decision tasks is presented. The results suggest that integration of certain behavioral theories as features in machine learning systems provides the best predictions. Surprisingly, the most useful theories for prediction build on basic properties of human and animal learning and are very different from mainstream decision theories that focus on deviations from rational choice. Moreover, we find that theoretical features should be based not only on qualitative behavioral insights (e.g. loss aversion), but also on quantitative behavioral foresights generated by functional descriptive models (e.g. Prospect Theory). Our analysis prescribes a recipe for derivation of explainable, useful predictions of human decisions.

[1]  J. Neumann,et al.  Theory of games and economic behavior , 1945, 100 Years of Math Milestones.

[2]  M. Allais.  Le comportement de l'homme rationnel devant le risque : critique des postulats et axiomes de l'ecole americaine , 1953 .

[3]  D. Bernoulli.  Exposition of a New Theory on the Measurement of Risk , 1954 .

[4]  M. Allais,et al.  Fondements d'une theorie positive des choix comportant un risque et critique des postulats et axiomes de l'ecole americaine , 1959 .

[5]  Hillel J. Einhorn,et al.  Expert measurement and mechanical combination , 1972 .

[6]  G. Teasdale.  Prediction in Action , 1978, Scottish medical journal.

[7]  W. Thorngate.  Efficient decision heuristics. , 1980 .

[8]  W. Güth,et al.  An experimental analysis of ultimatum bargaining , 1982 .

[9]  R. Dawes,et al.  Heuristics and Biases: Clinical versus Actuarial Judgment , 2002 .

[10]  A. Tversky,et al.  Advances in prospect theory: Cumulative representation of uncertainty , 1992 .

[11]  J. Townsend,et al.  Decision field theory: a dynamic-cognitive approach to decision making in an uncertain environment. , 1993, Psychological review.

[12]  J. Horowitz,et al.  Fairness in Simple Bargaining Experiments , 1994 .

[13]  Joyce E. Berg,et al.  Trust, Reciprocity, and Social History , 1995 .

[14]  Khadija Iqbal,et al.  An introduction , 1996, Neurobiology of Aging.

[15]  E. Fehr,et al.  When Social Norms Overpower Competition: Gift Exchange in Experimental Labor Markets , 1998, Journal of Labor Economics.

[16]  A. Diederich,et al.  Conflict and the Stochastic-Dominance Principle of Decision Making , 1999 .

[17]  Richard Gonzalez,et al.  On the Shape of the Probability Weighting Function , 1999, Cognitive Psychology.

[18]  I. Erev,et al.  Small feedback‐based decisions and their limited correspondence to description‐based decisions , 2003 .

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  E. Weber,et al.  Predicting Risk-Sensitivity in Humans and Lower Animals: Risk as Variance or Coefficient of Variation , 2004, Psychological review.

[21]  Alexander Strashny.  Asymmetric loss utility: an analysis of decision under risk , 2004 .

[22]  J. Payne.  It is Whether You Win or Lose: The Importance of the Overall Probabilities of Winning or Losing in Risky Choice , 2005 .

[23]  Philip H. Dybvig.  The Fallacy of Large Numbers , 2006 .

[24]  E. Yechiam,et al.  The Role of Personal Experience in Contributing to Different Patterns of Response to Rare Terrorist Attacks , 2005 .

[25]  R. Hertwig,et al.  The priority heuristic: making choices without trade-offs. , 2006, Psychological review.

[26]  Gordon D. A. Brown,et al.  Decision by sampling , 2006, Cognitive Psychology.

[27]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[28]  I. Erev,et al.  On the Descriptive Value of Loss Aversion in Decisions under Risk: Six Clarifications , 2007, Judgment and Decision Making.

[29]  Robert L. Slonim,et al.  Learning and equilibrium as useful approximations: Accuracy of prediction on randomly selected constant sum games , 2007 .

[30]  A. Glöckner,et al.  Do People Make Decisions Under Risk Based on Ignorance? An Empirical Test of the Priority Heuristic Against Cumulative Prospect Theory , 2008 .

[31]  M. Birnbaum,et al.  New Paradoxes of Risky Decision Making , 2022 .

[32]  Ryan K. Jessup,et al.  Feedback Produces Divergence From Prospect Theory in Descriptive Choice , 2008, Psychological science.

[33]  Neil Stewart,et al.  A decision-by-sampling account of decision under risk , 2008 .

[34]  I. Erev,et al.  Perceptual accuracy and conflicting effects of certainty on risk-taking behaviour , 2008, Nature.

[35]  Peter Norvig,et al.  The Unreasonable Effectiveness of Data , 2009, IEEE Intelligent Systems.

[36]  P. Wakker.  Prospect Theory: For Risk and Ambiguity , 2010 .

[37]  Cleotilde González,et al.  Effects of feedback and complexity on repeated decisions from description , 2011 .

[38]  E. Wagenmakers,et al.  Hierarchical Bayesian parameter estimation for cumulative prospect theory , 2011, Journal of Mathematical Psychology.

[39]  Leif D. Nelson,et al.  False-Positive Psychology , 2011, Psychological science.

[40]  Alvin E. Roth,et al.  A Choice Prediction Competition for Social Preferences in Simple Extensive Form Games: An Introduction , 2011, Games.

[41]  Amos Azaria,et al.  Combining psychological models with machine learning to better predict people’s decisions , 2012, Synthese.

[42]  A. Porcino.  The Next Frontiers , 2013, International journal of therapeutic massage & bodywork.

[43]  A. Roth,et al.  Maximization, learning, and economic behavior , 2014, Proceedings of the National Academy of Sciences.

[44]  J. Schreiber.  Foundations Of Statistics , 2016 .

[45]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[46]  Iyad Rahwan,et al.  The social dilemma of autonomous vehicles , 2015, Science.

[47]  T. Yarkoni,et al.  Choosing Prediction Over Explanation in Psychology: Lessons From Machine Learning , 2017, Perspectives on psychological science : a journal of the Association for Psychological Science.

[48]  Benjamin Manning,et al.  Extreme Gradient Boosting and Behavioral Biometrics , 2017, AAAI.

[49]  I. Erev,et al.  From Anomalies to Forecasts: Toward a Descriptive Model of Decisions Under Risk, Under Ambiguity, and From Experience , 2017, Psychological review.

[50]  V. S. Subrahmanian,et al.  Predicting human behavior: The next frontiers , 2017, Science.

[51]  Tomás Lejarraga,et al.  The Effect of Experience on Context‐dependent Decisions , 2018 .

[52]  J. Henrich,et al.  The Moral Machine experiment , 2018, Nature.

[53]  Jure Leskovec,et al.  Human Decisions and Machine Predictions , 2017, The quarterly journal of economics.

[54]  R. Baker,et al.  Mechanistic models versus machine learning, a fight worth fighting for the biological community? , 2018, Biology Letters.