Abstract: A system and a method are disclosed for optimally ranking and indexing accommodation listing information based on a set of constraints corresponding to a travel activity goal input on a client device. In an embodiment, an accommodation management system receives a travel activity goal input by a guest user on a client device with a corresponding set of constraints. Based on the constraints, the accommodation management system determines a set of geographic coordinates corresponding to the travel activity, and further identifies the set of candidate accommodation listings with accommodations within a threshold distance from the geographic coordinates. The accommodation management system filters and ranks the candidate accommodation listings based on the constraints, and sends a recommendation to the guest user for display on the client device which includes one or more of the ranked accommodation listings.

Abstract: A behavior detection module receives a training database and applies a transformation to the attributes that improves the uniformity of the values associated with each attribute. The transformed training database is used to construct a random forest classifier (RFC). The RFC includes a plurality of decision trees and generates a classification label estimate for a data entry with a plurality of attributes. The classification label estimate is determined based on classification estimates from the plurality of decision trees. Each parent node of a decision tree is associated with a condition of a transformed attribute that directs the data entry to a corresponding child node depending on whether the condition is satisfied or not. The data entry is directed through the tree to one out of a set of leaf nodes, and a classification label associated with the leaf node.

Abstract: A system and a method are disclosed for augmenting a required curriculum of an individual in a nomadic group. The system retrieves, from a client device, a request for an accommodation recommendation from the nomadic group, which includes an individual with a required curriculum. The system maps the curriculum to destinations in a destination database and determines a set of geographic regions including the destinations. The system optimizes an accommodation recommendation based on available listings in the geographic regions and geographic locations of the destinations and transmits, for display on a user interface at the client device, a user interface comprising the accommodation recommendation.

Abstract: Highly user-specific data is used to calculate user intent to make a purchase and the value of such a purchase. User activity and information is aggregated, per user, for a set window of time and real-time data on recent site behavior is obtained. Aggregated and/or real-time data is considered by a predictive intent model (calculating the probability that the user will make a purchase) and a predictive value model (calculating the expected revenue such a purchase may generate). Weights, specific to each model, are assigned to predictor features tracked in the aggregated and/or real-time user data. The most highly-weighted features of the intent model relate to users' viewing history, and the most highly-weighted features of the value model relate to price and market. By these means, a user conversion value can be obtained, guiding the application of user acquisition strategies for different home sharing markets.

Abstract: A user is associated with initial search requests, and results that comprise attribute types indicative of a common relationship with other results. Each result has an attribute parameter for each attribute type. Search interaction data. Search interaction data comprises attribute parameter data and user interaction data for the search results. A machine learning algorithm is trained to analyze the search interaction data to recognize common relationships, and used to detect a common relationship between the respective attribute parameters for one of the attribute types for which the user interest data indicates interest. When a subsequent search request is received from the user, a user interest characteristic is computed for each result, based on similarity between the attribute preference data detected using the machine learning algorithm and the attribute parameter for the attribute type. The search results are presented to the user, sorted according to user interest characteristic.

Abstract: A system and a method are disclosed for managing a travel itinerary by calculating pre-event triggers and interfacing with travel service providers to streamline travel services for a traveler. In an embodiment, a travel management system receives an electronic itinerary for a traveler, the electronic itinerary comprising a plurality of events. Based on the electronic itinerary, the travel management system identifies an event of the plurality of events and event managers for the events. The travel management system determines pre-event triggers for the events. The travel management system calculates trigger times for the pre-event triggers. The travel management system transmits, at the trigger times, the pre-event triggers to the event managers for execution of a function corresponding to the event.

Abstract: A method for predicting the behavior of an electronic social network (ESN) includes identifying one user's connections with other users and creating a data structure in a memory that represents the users and their connections in the ESN. A plurality of data sources for electronic communications between users are analyzed and assigned a relative importance value. A weight is also assigned to each of the connections between the users. The weight is an encoded value computed based on a link structure of the connections where the link structure includes metadata indicating a category and a status of the respective connection. The probability that one user will communicate with one of the other users is calculated based on the analyzed plurality of data sources calculating, and the user's connections with respect to other users are ranked based on the calculated probabilities.

Abstract: A position debiased search system can avoid bias towards top-ranked search results using a position-trained machine-trained model. Past positions for listings can be input into the model with added noise and low-ranked results to train the model to generate rankings that do not exhibit position bias. A network site can implement the position debiased search system to generate network site results that can generate accurate user results in real time as users browse the network site.

Abstract: A presentation service generates an audience interface for an electronic presentation. The audience interface may simulate an in-person presentation, including features such as a central presenter and seat locations for audience members. The audience members may select emotes which may be displayed in the audience interface. The emotes may indicate the audience members' opinion of the content being presented. The presentation service may enable chats between multiple audience members, grouping of audience members private rooms, and other virtual simulations of functions corresponding to in-person presentations.

Abstract: Highly user-specific data is used to calculate user intent to make a purchase and the value of such a purchase. User activity and information is aggregated, per user, for a set window of time and real-time data on recent site behavior is obtained. Aggregated and/or real-time data is considered by a predictive intent model (calculating the probability that the user will make a purchase) and a predictive value model (calculating the expected revenue such a purchase may generate). Weights, specific to each model, are assigned to predictor features tracked in the aggregated and/or real-time user data. The most highly-weighted features of the intent model relate to users' viewing history, and the most highly-weighted features of the value model relate to price and market. By these means, a user conversion value can be obtained, guiding the application of user acquisition strategies for different home sharing markets.

Abstract: A computer-implemented method of posting content to a social medium comprises receiving content posted by a user along with an associated posting time which indicates when the user selected an option to post the content to the social medium; determining that publication of the content posted by the user is dependent on a trigger; and in response to determining that publication of the content is dependent on the trigger, storing the content with the associated posting time and suspending publication of the content until the trigger is satisfied such that the posting time published with the content indicates a time prior to transmission of the content from an electronic device to a server for publishing.

Abstract: Systems and methods are disclosed for retrieving, from a database, over a network, historical routing data for multiple attributes and determining, for each attribute, based on its respective historical routing data, whether processing volume and processing error rates for each attribute exceed respective threshold. If both processing volume and error rate exceed their respective thresholds, the systems and methods describe herein calculate, for each qualifying attribute, a degree to which routing for each attribute can be improved. The systems and methods described herein output a ranking for each qualifying attribute based on their respective degrees to which routing can be improved for the respective attributes.

Abstract: A system and a method are disclosed for replacing a listing of a canceled booking for a guest user. In an embodiment, an accommodation management system receives an indication that a booking by the guest user has been canceled. The system retrieves, from an attribute database, attributes of the canceled listing and maps each attribute to a set of similar attributes in an equivalence table. The system retrieves, from a listing database, a set of comparable listings, each of which includes one or more of the mapped similar attributes and available during the same time period as the canceled booking. The system books one of the comparable listings for the guest user during the time period by populating a booking data structure with a connection between the comparable listing and the guest user.