Abstract: The disclosure is directed to systems, methods, and apparatus, including non-transitory computer-readable media, for performing quota resolution on a cloud computing platform. A system can receive user account data from one or more user accounts representing a first user. The system can generate a plurality of features from the user account data characterizing interactions between the first user and the computing platform. From at least the plurality of features, the system can generate a score at least partially representing a predicted likelihood that the additional computing resources allocated to the first user account will be used in violation of one or more predetermined abusive usage parameters during a predetermined future time period.

Abstract: A method for predicting a customer trust target metric includes receiving, from a business, a customer trust target metric definition defining a customer trust target metric customized by the business. The method also includes obtaining sentiment data representative of one or more interactions between a customer and the business. The sentiment data includes textual feedback data and non-textual metadata. The method also includes determining, using a natural language processing model, a sentiment score of the sentiment data. Further, the method includes predicting, using the sentiment score and the customer trust target metric definition, a respective customer trust target metric for a respective one of the one or more interactions between the customer and the business. The method also includes sending, to the business, the predicted respective customer trust target metric.

Abstract: The disclosure is directed to systems, methods, and apparatus, including non-transitory computer-readable media, for performing quota resolution on a cloud computing platform. A system can receive user account data from one or more user accounts representing a first user. The system can generate a plurality of features from the user account data characterizing interactions between the first user and the computing platform. From at least the plurality of features, the system can generate a score at least partially representing a predicted likelihood that the additional computing resources allocated to the first user account will be used in violation of one or more predetermined abusive usage parameters during a predetermined future time period.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for disambiguating word sense. One of the methods includes maintaining a respective word sense numeric representation of each of a plurality of word senses of a particular word; receiving a request to determine the word sense of the particular word when included in a particular text sequence, the particular text sequence comprising one or more context words and the particular word; determining a context numeric representation of the context words in the particular text sequence; and selecting a word sense of the plurality of word senses having a word sense numeric representation that is closest to the context numeric representation as the word sense of the particular word when included in the particular text sequence.