Recommender Systems were created to support users in situations of information overload. However, users are consciously or unconsciously influenced by many factors in their decision making. In this paper, we focused our attention on the influence of price in user decision-making in the context of online hotel search and booking. First, we analyzed a historical dataset from a meta-search booking platform to evaluate the influence of different factors on user click behavior. Then, we performed an online A/B test on the same meta-search booking platform, in which we compared the current policy with a price-based re-rank policy. Our experiments suggested that, although in offline observations properties with lower prices tended to have a higher Click-Through Rate, in an online context a price-based re-rank was only sufficient to achieve an improvement in Click-Through Rate for the first position on the recommended list.
Cavenaghi, E., Camaione, L., Minasi, P., Sottocornola, G., Stella, F., Zanker, M. (2022). An Online Experiment of a Price-Based Re-Rank Algorithm. In Proceedings of the Workshop on Recommenders in Tourism (RecTour 2022) co-located with the 16th ACM Conference on Recommender Systems (RecSys 2022) (pp.83-91). CEUR-WS.
An Online Experiment of a Price-Based Re-Rank Algorithm
Sottocornola, G;Stella, F;
2022
Abstract
Recommender Systems were created to support users in situations of information overload. However, users are consciously or unconsciously influenced by many factors in their decision making. In this paper, we focused our attention on the influence of price in user decision-making in the context of online hotel search and booking. First, we analyzed a historical dataset from a meta-search booking platform to evaluate the influence of different factors on user click behavior. Then, we performed an online A/B test on the same meta-search booking platform, in which we compared the current policy with a price-based re-rank policy. Our experiments suggested that, although in offline observations properties with lower prices tended to have a higher Click-Through Rate, in an online context a price-based re-rank was only sufficient to achieve an improvement in Click-Through Rate for the first position on the recommended list.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
