Revenue Maximization and Learning in Products Ranking

Abstract

We consider the revenue maximization problem for an online retailer who plans to display a set of products di ering in their prices and qualities and rank them in order. The consumers have random attention spans and view the products sequentially before purchasing a "satis cing" product or leaving the platform emptyhanded when the attention span gets exhausted. Our framework extends the cascade model in two directions: the consumers have random attention spans instead of xed ones and the rm maximizes revenues instead of clicking probabilities. We show a nested structure of the optimal product ranking as a function of the attention span when the attention span is xed and design a 1/𝑒-approximation algorithm accordingly for the random attention spans. When the conditional purchase probabilities are not known and may depend on consumer and product features, we devise an online learning algorithm that achieves Õ ( √ 𝑇 ) regret relative to the approximation algorithm, despite of the censoring of information: the attention span of a customer who purchases an item is not observable. Numerical experiments demonstrate the outstanding performance of the approximation and online learning algorithms.

Online Learning of Independent Cascade Models with Node-level Feedback

“…Furthermore, OIM falls in the Combinatorial Multi-Armed Bandit (CMAB) regime, where each arm is a combination of multiple selected items. CMAB has found widespread applications in the real-world, such as assortment optimization (Agrawal et al 2019, Oh and Iyengar 2021, and product ranking (Chen et al 2020). Most CMAB models assume semi-bandit feedback, where the agent can observe the outcome of every item within the selected arm (Gai et al 2012, Chen et al 2013, Kveton et al 2015c, Chen et al 2016b, Wang and Chen 2017, or partial-feedback, where the agent can only observe a subset of the selected items (Kveton et al 2015b, Combes et al 2015, Katariya et al 2016, Zong et al 2016, Cheung et al 2019.…”

Sequential Choice Bandits with Feedback for Personalizing users' experience

“…The work in (Kveton, Szepesvari, Wen, & Ashkan, 2015;Cao, Sun, & Shen, 2019;Chen, Li, & Yang, 2020) studies variants of sequential choice bandit model without feedback. Unlike our setting, the sequence of action is pre-determined at the arrival of each user, independently from the user's feedback.…”