Abstract: A network computing system to provide an account management service for guiding user actions and providing users with information to facilitate decision making. In providing the account management services, the network computer system makes predictive determinations about the actions of service providers, in connection with specific actions of individual users.

Abstract: A method may include obtaining interactions between users and items, and calculating, for each edge in a bipartite graph, an edge weight using an inverse of the degree of a user node connected to the edge and an inverse of the degree of an item node connected to the edge. The bipartite graph includes user nodes corresponding to the users and item nodes corresponding to the items. The method may further include identifying paths each including an edge connecting the target user node and a common item node, an edge connecting a neighboring user node and the common item node, and an edge connecting the neighboring user node and a neighboring item node. The method may further include calculating, using the edge weights calculated for the edges, scores for the paths, and recommending, to the target user and using the scores for the paths, a recommended item.

Abstract: A method may include obtaining interactions between users and items, and calculating, for each edge in a bipartite graph, an edge weight using an inverse of the degree of a user node connected to the edge and an inverse of the degree of an item node connected to the edge. The bipartite graph includes user nodes corresponding to the users and item nodes corresponding to the items. The method may further include identifying paths each including an edge connecting the target user node and a common item node, an edge connecting a neighboring user node and the common item node, and an edge connecting the neighboring user node and a neighboring item node. The method may further include calculating, using the edge weights calculated for the edges, scores for the paths, and recommending, to the target user and using the scores for the paths, a recommended item.

Abstract: A method and apparatus for detecting and engaging participants in an online course that are not likely to attend the online course, is presented herein. Participants in an online course are responsible for attending the course by downloading instructional material and completing assignments through an online forum. Attending the online course causes interaction data and/or performance data to be generated and stored for each participant. The interaction and performance data for a particular participant may be analyzed to determine whether the particular participant is likely to not attend the online course during a future period. If the particular participant is not likely to attend the online course during the future period, an alert is a counselor to intervene and engage the participant. A counselor may follow up with the particular participant to make sure the participant is on track to attend and complete the online course.