Bounded Cognition and Representativeness in Forecasting

Most operations models assume that individuals have perfect beliefs about random variables or stochastic processes. In reality, however, individuals make judgment errors and are subject to predictable biases. We leverage two fundamental psychological principles bounded cognition and representativeness to model individuals' forecasting errors and biases in a way that is portable to operations models. The model has only one behavioral parameter and embeds perfect rationality as a special case. We use the model to mathematically characterize point forecast and error forecast behavior, re ecting an individual's beliefs about the mean and variance of a random variable, respectively. We then derive several distinct behavioral phenomena generated by the model and discuss how these behaviors relate to existing eld and experimental evidence. Finally, we apply the model to two important operations management contexts inventory management and queuing to demonstrate the model's portability to operations settings.