On the Efficiency of Social Learning

We revisit well-known models of learning in which a sequence of agents make a binary decision on the basis of a private signal and additional information. We introduce efficiency measures, aimed at capturing the speed of learning in such contexts. Whatever the distribution of private signals, we show that the learning efficiency is the same, whether each agent observes the entire sequence of earlier decisions, or only the previous decision. We provide a simple necessary and sufficient condition on the signal distributions under which learning is efficient. This condition fails to hold in many prominent cases of interest. Extensions are discussed.

[1]  Elchanan Mossel,et al.  On the Speed of Social Learning , 2014, SSRN Electronic Journal.

[2]  Michael Rapp,et al.  Observational Learning with Position Uncertainty , 2014, J. Econ. Theory.

[3]  I. Lobel,et al.  Information Diffusion in Networks through Social Learning , 2014 .

[4]  Jérôme Renault,et al.  Repeated Games with Incomplete Information , 2009, Encyclopedia of Complexity and Systems Science.

[5]  Douglas Gale,et al.  Bayesian learning in social networks , 2003, Games Econ. Behav..

[6]  Lones Smith,et al.  Rational Social Learning by Random Sampling , 2013 .

[7]  M. Benaïm.  Dynamics of stochastic approximation algorithms , 1999 .

[8]  Matthew O. Jackson,et al.  Naïve Learning in Social Networks and the Wisdom of Crowds , 2010 .

[9]  Omer Tamuz,et al.  The speed of sequential asymptotic learning , 2017, J. Econ. Theory.

[10]  Elchanan Mossel,et al.  Strategic Learning and the Topology of Social Networks , 2012, ArXiv.

[11]  Itai Arieli,et al.  Inferring Beliefs from Actions , 2016, Games Econ. Behav..

[12]  Shachar Kariv,et al.  Observational learning under imperfect information , 2004, Games Econ. Behav..

[13]  Nicolas Vieille,et al.  Informational externalities and emergence of consensus , 2009, Games Econ. Behav..

[14]  Asuman E. Ozdaglar,et al.  Opinion Dynamics and Learning in Social Networks , 2010, Dyn. Games Appl..

[15]  A survey of random processes with reinforcement , 2007, math/0610076.

[16]  P. DeMarzo,et al.  Persuasion Bias, Social Influence, and Uni-Dimensional Opinions , 2001 .

[17]  Drew Fudenberg,et al.  Word-of-mouth learning , 2004, Games Econ. Behav..

[18]  Munther A. Dahleh,et al.  Rate of Convergence of Learning in Social Networks , 2009 .

[19]  S. Bikhchandani,et al.  You have printed the following article : A Theory of Fads , Fashion , Custom , and Cultural Change as Informational Cascades , 2007 .

[20]  A. Banerjee,et al.  A Simple Model of Herd Behavior , 1992 .

[21]  Elchanan Mossel,et al.  Asymptotic learning on Bayesian social networks , 2012, Probability Theory and Related Fields.

[22]  C. Chamley.  Rational Herds: Economic Models of Social Learning , 2003 .

[23]  Lones Smith,et al.  Pathological Outcomes of Observational Learning , 2000 .