Funded Phd Research
Innovations in Pricing Strategy
Business Economics and Public Policy Department; Faculty Adviser: Judd B. Kessler
Online retailers collect a wealth of information on shopping behavior, and they face a unique opportunity to leverage these data to determine profit-maximizing prices. Combining the predictive power of machine learning and insights from the neuroeconomics literature, we propose a novel approach to estimate an individual customer’s willingness to pay for a good based on binary choice data (i.e., whether the customer would buy the good at a given price) and decision times (i.e., how long it took the customer to decide whether to buy the good at that price).
Models of decision making from the psychology and neuroscience literature show that difficult decisions require more decision time. Intuitively, a consumer who is close to indifferent between purchasing and not purchasing a good must take longer to determine if the purchase is a good decision. We hypothesized that we could invert the relationship: by observing a consumer’s binary purchasing decision and decision time, we believed we could predict their willingness to pay for the good.