Learning to Sell a Focal‐Ancillary Combination

ABSTRACT A number of products are sold in the following sequence: first, an essential focal product is presented, and if purchased, discretionary ancillary products are subsequently offered. Examples include airline flights followed by seat selection or insurance, hotel rooms followed by spa treatments, and electronics such as tablets paired with accessories like electronic pencils. The firm has to decide on a sale format—whether to sell them in sequence, unbundled or together as a bundle—and how to price them. Since the discretionary ancillary is considered by the customer only after the purchase of the focal product, the sale strategy chosen by the firm creates an information and learning dependency between the products: for instance, offering only a bundle would preclude learning customers' valuation for the focal and ancillary products individually. In this paper, we study learning strategies for such focal and ancillary item combinations under the following scenarios: (a) pure unbundling to all customers, (b) a personalized mechanism, where, depending on some observed features of the customers, the two products are presented and priced as a bundle or in sequence, and (c) the firm can change the selling strategy only once over the entire time horizon. We design pricing algorithms for all three scenarios assuming a demand distribution that depends on a linear function of customer features and show that their regrets are upper bounded by , where denotes the dimension of the customer features and represents the time horizon. Furthermore, we conduct numerical experiments with both simulated and real‐world data to demonstrate the effectiveness of the proposed algorithms.