Observational Learning with Fake Agents

It is common in online markets for agents to learn from other’s actions. Such observational learning can lead to herding or information cascades in which agents eventually "follow the crowd". Models for such cascades have been well studied for Bayes-rational agents that choose pay-off optimal actions. In this paper, we additionally consider the presence of fake agents that seek to influence other agents into taking one particular action. To that end, these agents take a fixed action in order to influence the subsequent agents towards their preferred action. We characterize how the fraction of such fake agents impacts behavior of the remaining agents and show that in certain scenarios, an increase in the fraction of fake agents in fact reduces the chances of their preferred outcome.

[1]  Vijay Subramanian,et al.  Social learning with questions , 2018, NetEcon@SIGMETRICS.

[2]  I. Welch.  Sequential Sales, Learning, and Cascades , 1992 .

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

[4]  Lee In Ho.  On the Convergence of Informational Cascades , 1993 .

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

[6]  Asuman E. Ozdaglar,et al.  Opinion Fluctuations and Disagreement in Social Networks , 2010, Math. Oper. Res..

[7]  Achilleas Anastasopoulos,et al.  Characterizing Non-Myopic Information Cascades in Bayesian Learning , 2018, 2018 IEEE Conference on Decision and Control (CDC).

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

[9]  Randall Berry,et al.  Bayesian Learning with Random Arrivals , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[10]  Yangbo Song,et al.  Social Learning with Endogenous Network Formation , 2015, ArXiv.

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

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

[13]  M. Mobilia.  Does a single zealot affect an infinite group of voters? , 2003, Physical review letters.

[14]  Yuval Peres,et al.  How fragile are information cascades? , 2017, The Annals of Applied Probability.

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

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