Abstract
Traditional choice models assume that consumers have well-defined preferences and are not influenced by additional information. However, consumers do not always behave rationally in making purchase decisions. To capture consumers' irrational behaviors and make a more accurate market demand prediction, this paper reports the development of a behavioral choice model that covers reference dependence, diminishing sensitivity and loss aversion in assigning value to each product attribute. The utility of a product is formulated as a weighted sum of all interested attribute values and an unobserved noise factor. A choice probability is then derived from the utility function under the first choice rule with the assumption that unobserved factors are independently identically distributed extreme values. A case study is conducted and the behavioral choice model is demonstrated to outperform logit choice model with smaller squared error for predicting product demand.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have