Abstract: Some aspects relate to technologies for category recommendation for a listing platform using a cascading category recommender. The cascading category recommender includes a candidate category model, a per-user category encoder, and a category prediction model. Given a sequence of interacted categories for a user, the candidate category model selects candidate categories from a category set that sets forth categories for item listings on a listing platform. The per-user category encoder generates a category embedding for each interacted category based on interacted items for the user corresponding to each interacted category. The category prediction model selects categories for recommendation using the candidate categories, the sequence of interacted categories, and the category embeddings.

Abstract: A method of displaying a user interface is provided. The method includes retrieving reviews for an item and extracting indicia from the retrieved reviews. A first question is generated based on the extracted indicia. A first interactive user interface is displayed that includes the first question along with an option to provide a response that corresponds to a review of the item. A second question and an answer to the second question are generated based on the response to the first question. A second interactive user interface that includes the second question and the answer to the second question is then displayed.