611 / 2024-04-27 09:46:04

Consumer preference estimation based on intertemporal choice data: A chance-constrained data envelopment analysis method

Data envelopment analysis; Intertemporal Choices; Stochastic variable; Preference estimation; Choice Prediction

Choice behavior reflects consumer preferences. Consumers often purchase products online nowadays, which can be viewed as a choice process. If a consumer makes multiple transactions over a period of time, then we can say the consumer make multiple intertemporal choices. This study mainly investigates consumer reference learning problem based on intertemporal choices data. Two challenges should to be addressed, one is that the offered candidate items (choice set) are varying at different time, the other is that some attributes of item are uncertain. The current study develops a consumer preference model based on the framework of chance constrained data envelopment analysis (DEA) method. In the model, we assume consumer choice has maximum utility value, and define a performance cost utility function. Then, according to whether the uncertain variables are correlated, the consumer preference models are developed in two scenarios. We can use the estimated consumer preferences to predict each consumer’s choice and item ranking. To verify the validity of our model, we conduct two numerical experiments, and analyze the results under different values of risk indicator and correlation coefficients. The results show that the estimated preference value is accurate when the values of risk indicator and correlation coefficients are small, and our model performs well on the prediction of choice and item ranking.