Premium
Learning with Projection Effects in Service Operations Systems
Author(s) -
He QiaoChu,
Chen YingJu,
Righter Rhonda
Publication year - 2020
Publication title -
production and operations management
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.279
H-Index - 110
eISSN - 1937-5956
pISSN - 1059-1478
DOI - 10.1111/poms.13093
Subject(s) - queue , service (business) , bounded rationality , computer science , service quality , quality (philosophy) , rationality , bounded function , service system , population , projection (relational algebra) , microeconomics , social welfare , operations research , business , marketing , economics , artificial intelligence , computer network , mathematics , algorithm , mathematical analysis , philosophy , demography , epistemology , sociology , political science , law
In this paper, we study customers’ learning behaviors in service operations systems, when the customers hold incorrect beliefs about the population distribution (“projection effects”). We propose a basic model wherein the customers are heterogeneous in both delay sensitivity and awareness of service quality, which explains “rational hesitations”: The uninformed and patient customers obfuscate the quality signaled by the queue length for the uninformed and impatient customers, who wait and join when the queue becomes longer. Ironically, with such bounded rationality, the customers who are more averse to waiting will react more sensitively to the observed long queue, which leads to an overestimation of the service quality and waiting in the long queue. Such bounded rationality also impedes effective learning by inducing decision errors, which, among other consequences, reduces the social welfare due to a blind “buying frenzy” even if the service quality is low.