Abstract: Systems and methods for predicting user actions based upon electronic communication between a user and an organization are disclosed. Based upon user interactions with an organization via electronic communication channels (e.g., e-mail, electronic chat, or voice/video calls), a trained predictive model is used to predict a probability of a future user action relating to the organization. Such user electronic communication is processed to generate message features from message content and metadata, which message features are then combined with other user data features associated with the user or with user interaction with an electronic data system of the organization. The combined data set of message features and user data features is analyzed by the predictive model to generate an output value indicative of a predication of a future user action.

Abstract: Systems and methods for providing information regarding vehicle inventory availability to users of an information system are disclosed. When generating a vehicle data page for a particular vehicle at a particular location, the information system may generate an expected duration of availability of the vehicle as a prediction of the time between listing and sale of the vehicle. When the expected duration of availability is below a threshold, a status indicator may be generated and added to the vehicle data page to alert users that the vehicle is expected to remain available for only a short period of time. An estimate of time remaining for the vehicle may also be generated and presented to users as part of the vehicle data page.