How fragile are information cascades?

It is well known that sequential decision making may lead to information cascades. That is, when agents make decisions based on their private information, as well as observing the actions of those before them, then it might be rational to ignore their private signal and imitate the action of previous individuals. If the individuals are choosing between a right and a wrong state, and the initial actions are wrong, then the whole cascade will be wrong. This issue is due to the fact that cascades can be based on very little information. We show that if agents occasionally disregard the actions of others and base their action only on their private information, then wrong cascades can be avoided. Moreover, we study the optimal asymptotic rate at which the error probability at time $t$ can go to zero. The optimal policy is for the player at time $t$ to follow their private information with probability $p_{t} = c/t$, leading to a learning rate of $c'/t$, where the constants $c$ and $c'$ are explicit.

[1]  D. Freedman.  On Tail Probabilities for Martingales , 1975 .

[2]  I. Welch,et al.  On the Evolution of Overconfidence and Entrepreneurs , 2001 .

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

[4]  A. Tversky,et al.  On the psychology of prediction , 1973 .

[5]  Asuman Ozdaglar,et al.  Fast and Slow Learning from Reviews , 2017 .

[6]  Charles A. Holt,et al.  Information Cascades in the Laboratory , 1998 .

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

[8]  Ilan Lobel,et al.  BAYESIAN LEARNING IN SOCIAL NETWORKS , 2008 .

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

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

[11]  Yu Cheng,et al.  A Deterministic Protocol for Sequential Asymptotic Learning , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[12]  Randall Berry,et al.  Information Cascades With Noise , 2017, IEEE Transactions on Signal and Information Processing over Networks.

[13]  Chris Arney,et al.  Networks, Crowds, and Markets: Reasoning about a Highly Connected World (Easley, D. and Kleinberg, J.; 2010) [Book Review] , 2013, IEEE Technology and Society Magazine.

[14]  E. David,et al.  Networks, Crowds, and Markets: Reasoning about a Highly Connected World , 2010 .

[15]  Daniel Sgroi,et al.  Optimizing Information in the Herd: Guinea Pigs, Profits, and Welfare , 2002, Games Econ. Behav..

[16]  Shachar Kariv,et al.  Distinguishing Informational Cascades from Herd Behavior in the Laboratory , 2004 .

[17]  R. Agrawal.  Sample mean based index policies by O(log n) regret for the multi-armed bandit problem , 1995, Advances in Applied Probability.

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

[19]  Elchanan Mossel,et al.  Groupthink and the Failure of Information Aggregation in Large Groups , 2014 .

[20]  Moe Z. Win,et al.  On the Subexponential Decay of Detection Error Probabilities in Long Tandems , 2007, IEEE Transactions on Information Theory.

[21]  Petar M. Djuric,et al.  Social Learning With Bayesian Agents and Random Decision Making , 2015, IEEE Transactions on Signal Processing.

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

[23]  T. L. Lai Andherbertrobbins.  Asymptotically Efficient Adaptive Allocation Rules , 2022 .

[24]  E. Todeva.  Networks , 2007 .

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

[26]  T. Cover.  Hypothesis Testing with Finite Statistics , 1969 .

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

[28]  John N. Tsitsiklis,et al.  On Learning With Finite Memory , 2012, IEEE Transactions on Information Theory.