Abstract: A method may include identifying a dataset corresponding to an entity. The dataset may include characteristics of the entity, historic actions performed by the entity, and historic events involving the entity. The historic actions can be associated with one or more products or services. The method may include generating a hierarchy data structure corresponding to the entity based on the dataset. The hierarchy data structure can define a first data level for a first subset of the dataset and a second data level for a second subset of the dataset. The method may include generating a feature set based on a first featurization process applied to the first subset and a second featurization process applied to the second subset. The method may include executing a machine-learning model associated with the entity using the feature set as input.

Abstract: Methods and systems for providing new functionality in chat applications are provided. In one embodiment, the new methods and systems associate commands with particular characters appearing in a chat message which instruct the chat application to perform certain protocols. In one embodiment, an application identifies a keyword in the chat message and performs an electronic search for data on the keyword. The search results may then be modified based on location; personal preferences and rankings, as well as preferences and rankings of the designated friends of the users involved in the online chat discussion.