| While a significant literature has emerged recently on the long-term effects of price promotions, as inferred from persistence models, there is very little if any attention paid to whether such long-term effects vary across different types of consumers. We use two different approaches to address this issue: (1) a priori segmentation method to explore whether the adjustment, permanent, and total effects of price promotions and the duration of the adjustment period differ between consumers segmented based on their usage rates in a product category and their loyalty to a brand, and (2) finite mixture segmental hidden Markov model to classify consumers based on their long-term response patterns to a promotion.; For the first approach, expectations are developed based on consumer behavior theory on various effects of price promotions, such as the post deal trough, the mere purchase effect, the promotion usage effect, and responsiveness to competitor's reactions, and evidence from household level supermarket scanner data from four product categories is provided. We find substantial differences between consumer segments, in providing insights on how managers can increase the long-term effectiveness of price promotions by targeting each consumer segment with a different promotion program. In addition, consumer segmentation is found to improve the forecasting performance of the persistence model, in particular when segmentation results in increased variation in total quantity sold across weeks.; For the second approach, we first estimate VARX models and generated impulse response functions for each household. A finite mixture segmental hidden Markov model is applied to the individual-level impulse response functions to classify households into segments based on their long-term response patterns. We find a multiple segment solution is better than a single segment solution in terms of BIC criteria indicating again the existence of consumer heterogeneity in long-term effects of promotions. The segments are found to differ on the average duration of adjustment periods. Finally, we describe each segment based on characteristics of their purchase behavior. |
