Abstract: An online system trains a constraint prediction machine-learning model using an action-based loss function. The action-based loss function computes a weighted sum of (1) an accuracy of the constraint prediction model in predicting whether a user's interaction complies with a set of constraints and (2) an action score representing a number of actions taken by users to determine whether the user's action complies with the set of constraints. The online system may apply this trained constraint prediction model to future interaction data received from third-party systems to predict whether user interactions with those third-party systems comply with the set of constraints.

Abstract: A method for displaying and dynamically updating a user interface displaying a listing of air tickets available for purchase on a flight includes receiving, by a computing device, a plurality of search results including at least one fare listing for an air ticket for a seat on a flight and unstructured data including at least one rule associated with the search result. The computing device assigns an initial quality rating for each of the plurality of search results. The computing device receives, for each of the plurality of search results, structured data identifying at least one amenity and analyzes the received structured and unstructured data. The computing device assigns a modified quality rating to at least one of the plurality of search results and displays, to a second computing device, an enumeration of each of the plurality of search results categorized based on the quality ratings.