Abstract: A system and method for generating and providing personalized virtual property tours are disclosed. In some examples, a system provides a virtual property tour that is displayed within an application or a web browser as an interactive open house experience. The virtual property tour enables a user to view an open house virtually through a display of a floor plan, photos of rooms, videos of rooms, three-dimensional tours of rooms, and/or a virtual interactive engagement with rooms. In some embodiments, the virtual property tour is user-directed by selecting a room or other location from a virtual floor plan. In other embodiments, the virtual property tour is configured as an automated progression through a property.

Abstract: Methods, apparatus, and systems are disclosed that determine property recommendations for a user. The methods, apparatus, and systems may also predict when a user is likely to become a property buyer and/or seller to determine when certain property recommendations are to be made. The methods, apparatus, and systems use one or more machine learning algorithms to determine a dynamic preference profile for a user that accurately reflects the user and how the user changes over time. The preference profile takes into account property-related information and user characteristic information as variables for the machine learning algorithm(s).

Abstract: A system and method for generating a dynamic real estate ticker for a user device are disclosed. An example method includes storing property transaction information and property-related web browsing information that is related to a user. The method also includes determining a real estate state of the user, among a plurality of available real estate states, based on the property transaction information and the property-related web browsing information. The plurality of available real estate states includes at least three of a first-time buyer, a repeat-buyer, a new owner, a mid-term owner, a long-term owner, a renter, an owner-renter, a seller, or an investor. The method further includes determining real estate content for the dynamic ticker based on the determined real estate state of the user and the property-related web browsing information. The determined real estate content is transmitted to the user device for display within a dynamic ticker.

Abstract: A computer-implemented method for constructing network activity profiles is provided, which comprises the following: obtaining a plurality of records of network activities from an activity source, each record corresponding to an interaction with a network resource via the network from the activity source, wherein each record comprises at least a network endpoint address from where the interaction originates and an indication of a time of the interaction; for each record, determining a geographical location corresponding to the network endpoint address of that record and associating the determined geographical location with that record; and constructing at least one profile for the activity source based on the plurality of records and at least one geographical location associated with the records, wherein each profile comprises a time-based behavior pattern associated with the at least one geographical location.

Abstract: A computer-implemented method for constructing network activity profiles is provided, which comprises the following: obtaining a plurality of records of network activities from an activity source, each record corresponding to an interaction with a network resource via the network from the activity source, wherein each record comprises at least a network endpoint address from where the interaction originates and an indication of a time of the interaction; for each record, determining a geographical location corresponding to the network endpoint address of that record and associating the determined geographical location with that record; and constructing at least one profile for the activity source based on the plurality of records and at least one geographical location associated with the records, wherein each profile comprises a time-based behavior pattern associated with the at least one geographical location.