Expedia, Inc.

One embodiment relates to a method for searching for travel items. The method includes obtaining interaction data indicating a set of interactions of a first user across a plurality of platforms. The method includes generating a dynamic user profile indicating a plurality of travel preferences for the first user. The method includes generating search suggestions for the first user based on the dynamic user profile, the search suggestions specific to the first user and generated based at least in part on characteristics of the dynamic user profile. The search suggestions include at least one of suggested search queries or suggested filters. The method includes receiving a selection from the first user of a first search suggestion. The method includes identifying a first plurality of travel items using the selected first search suggestion. The method includes providing, to the first user, the first plurality of travel items.

Systems and methods for providing improved graphical user interfaces are disclosed. A method includes: receiving experience information associated with an experience; evaluating the experience information based on contextual information associated with the experience; determining a priority of the experience information based on the evaluation; retrieving a digital object template from a limited number of digital object templates based on the determined priority of the experience information; populating the retrieved digital object template with corresponding experience information to generate a contextual digital interface object; and providing the contextual digital interface object on a graphical user interface of a user device, the contextual digital interface object comprising a selectable feature based on the corresponding experience information.

Systems and methods are described for providing personalized travel experiences to a user. In some implementations, a user query related to a request to generate travel recommendations is obtained. The systems and methods can access the user data store to obtain user profile data. Based at least in part of the user profile data, the systems and methods can utilize a case-specific user analysis model to determine the user's specific travel preferences. Based at least in part on the user's specific travel preferences and query, the systems and methods can generate a prompt to input to an LLM. The LLM can output personalized travel recommendations based at least in part on the input prompt to provide to the user.

A computing system includes a processing circuit having a processor coupled to a memory device. The processing circuit performs operations including receiving, during a search session, a search query comprising configurable parameters; providing, during the search session, an array of visual outputs that meet criteria defined by the parameters; receiving, from a user device, during the search session, a selection of a visual output from the array; extracting, using a machine learning model and based on a pixel composition of the visual output, a feature; identifying, using the machine learning model, one or more second visual outputs related to travel properties that share the feature; replacing a default image associated with at least one travel property with an image representing the feature; and providing, to the user device, during the search session, a second array comprising the one or more second visual outputs including the replaced image.

Systems and methods of recommending insights to optimize an experience. In some implementations, a request is received to optimize an experience based on a display option of a plurality of display options, one or more filters, and/or one or more metrics. Based on the request, the systems and methods can access (e.g., from a sampled data set) metric data associated with each of the display options. Metric data corresponding to each display options can be compared to generate insights based on each comparison. The systems and methods can determine whether an insight corresponds to a positive improvement and rank the insights based on preconfigured criteria. In addition, insights can be implemented automatically and/or recommended to a user in order to optimize the experience (e.g., based on the one or more metrics).

A system includes at least one processing circuit including at least one memory and one or more processors configured to: identify, via at least one machine learning model, at least one excluded parameter of a non-bounded query relating to a trip; identify, via the at least one machine learning model, a set of travel results that match the query and the excluded parameter by: analyzing, based on search data from one or more users, at least one search result distribution corresponding to at least one parameter associated with at least one trip of the one or more users and relating to the at least one excluded parameter; and identifying the set of travel results based on a value regarding the at least one parameter satisfying a presentation threshold for the at least one search result distribution; and present one or more travel results of the set of travel results.

A computing system includes a processing circuit having at least one processor coupled to at least one memory device. The processing circuit performs operations including receiving, from a user device during a search session, a first visual output from a first array of visual outputs comprising a first set of configurable parameters; extracting, using a machine learning model, at least one feature of the first visual output based on a characteristic of the first visual output; identifying, using the machine learning model, one or more second visual outputs that share the at least one feature of the first visual output based on a characteristic of each of the one or more second visual outputs; generating a second array of visual outputs comprising the one or more second visual outputs; and displaying, via a user interface of the user device and during the search session, the second array of visual outputs.

A system includes at least one processing circuit including at least one memory and one or more processors configured to: obtain, via a user interface, a non-bounded query relating to a travel trip, the non-bounded query excluding at least one parameter associated with the travel trip; identify, via a first machine learning model, the at least one excluded parameter based on the non-bounded query; identify, via a second machine learning model and from among a first set of travel results that match the non-bounded query and the excluded parameter, a second set of the travel results that meet a presentation threshold of customer popularity based on at least one of a location selected by one or more users or a time selected by the one or more users; and present, via the user interface, one or more travel results of the second set, and the presentation threshold.

Systems and methods for a two-part recommendation system wherein a non-personalized item-to-candidate item list is generated without personalization and the items within the corresponding candidate list may be ranked in order to personalize that list to the particular user. In an embodiment, ranking occurs based on a distance function between individual items in the list and the reference item, such as a distance between the items within an embedding space that represents relevant features of items as vectors in latent space. Accordingly, ranking by a candidate ranker can select which items in the candidate list are most pertinent and personalized to the user at a present time. Because ranking can require significantly fewer resources than generating the candidate list, this two-part system can enable real-time recommendations that are personalized to the user.

Systems and methods are provided for data intake of data from an ingestion service indicating a user's online or offline behavior with respect to a domain. A domain persona system may receive a request to access an ingestion service. The domain persona system may then access the ingestion service to obtain the data and identify a subset of the data relevant to the user's online or offline behavior with respect to the domain. The domain persona system may further generate insights with respect to the identified subset and output at least one of the identified subset and the generated insights to a system that updates the domain persona.