Deep Contextual Bandits for model selection in travel e-commerce

We use learning to rank, sequence-based recommendation models, content or behavior representation-based algorithms, and collaborative filtering algorithms too. After the customer browses around, searching for hotels in city A, B or C, a substantial portion search for a single hotel and look at the responses/price/content to review. For such "direct hotel search" scenarios, it is prudent to show a few alternatives as well, for customers to compare and contrast them. More important if alternative hotels can bring higher value preposition to the business or to the customer (for ex., better service/value for same price). In this scenario, one could recommend hotels similar to the pivot hotel user has searched.