Abstract: Indications of interest can be automatically generated. For example, attributes of an item can be received. There can be little or no historical data for the item. Multiple time series associated with other items can also be received. A first set of classifiers can identify a subset of magnitude-pattern groups based on the attributes. A first ensemble methodology can select a final magnitude-pattern group for the item from among the subset of magnitude-pattern groups. A second set of classifiers can determine a subset of interest volumes based on the attributes. A second ensemble methodology can select a final interest volume for the item from among the subset of interest volumes. Interest data can be generated based on the final magnitude-pattern group and the final interest volume. The interest data can provide an initial indication of interest in the item over a future time period.

Abstract: In certain embodiments, a method for modeling interactions with a computer system includes collecting interaction information for each of a number of interaction sessions with a computer system, each interaction session being associated with a corresponding agent system and including one or more states and one or more state transitions. The interaction information for an interaction session includes data for the one or more states and the one or more state transitions of the interaction session. The method further includes, for each of the interaction sessions, identifying the one or more states encountered during the interaction session based on the collected interaction information and generating, based on the one or more states encountered during the interaction session, a trace of the interaction session. The method further includes generating, based on the traces of the interaction sessions, a model of the interaction sessions, the model including the traces for each of the interaction sessions.

Abstract: In certain embodiments, a method for modeling interactions with a computer system includes collecting interaction information for each of a number of interaction sessions with a computer system, each interaction session being associated with a corresponding agent system and including one or more states and one or more state transitions. The interaction information for an interaction session includes data for the one or more states and the one or more state transitions of the interaction session. The method further includes, for each of the interaction sessions, identifying the one or more states encountered during the interaction session based on the collected interaction information and generating, based on the one or more states encountered during the interaction session, a trace of the interaction session. The method further includes generating, based on the traces of the interaction sessions, a model of the interaction sessions, the model including the traces for each of the interaction sessions.

Abstract: A method includes receiving a plurality of events that each include a plurality of associated attributes, analyzing the plurality of associated attributes in order to identify at least two or more related events, determining a time associated with each of the at least two or more related events from the plurality of associated attributes, ordering the at least two or more related events in chronological order based on the determined time associated with each of the at least two or more related events, and manipulating at least one of the at least two or more related events based on the ordering.

Abstract: A method includes receiving a plurality of events that each include a plurality of associated attributes, analyzing the plurality of associated attributes in order to identify at least two or more related events, determining a time associated with each of the at least two or more related events from the plurality of associated attributes, ordering the at least two or more related events in chronological order based on the determined time associated with each of the at least two or more related events, and manipulating at least one of the at least two or more related events based on the ordering.

Abstract: According to one embodiment of the disclosure, a computerized method for modeling business processes includes receiving, at a computer, interaction data for interaction sessions. The interaction data includes session states indicative of session screens. The interaction data further includes transitions between the session states. The computerized method also includes identifying, at the computer, business processes based on the interaction data. The computerized method further includes identifying, at the computer, instances of the business processes in the interaction data. The computerized method further includes storing the instances as event records. The event records include a parameter indicative of a corresponding business process. The computerized method further includes generating a model based on the event records.