Abstract: A method includes inputting used oil analysis data to a pre-trained predictive model, the used oil analysis data including values quantifying a plurality of chemical components measured in a sample of used oil taken from an engine under analysis, determining a probability of at least one fail code with the pre-trained predictive model in response to the used oil analysis data, the at least one fail code corresponding to one of a plurality of predetermined engine failure types, providing the at least one fail code and the probability of the at least one fail code to an expert system, performing with the expert system a root cause analysis of the at least one fail code determine a root cause indicating a preventative maintenance action, and performing the predictive maintenance action on the engine under analysis.

Abstract: Techniques are described herein that are capable of automatic mapping of a question or compliance controls associated with a compliance standard to compliance controls associated with another compliance standard. Reference controls having respective first subsets of text-based features are identified. A question having a second subset of the text-based features or custom controls having respective second subsets of the text-based features are identified. Scores for the respective reference controls are determined for the question or each custom control using a supervised natural language processing machine learning model based at least on the first subsets of the text-based features and the second subset(s) of the text-based features. A compliance map is generated by automatically mapping the question or each custom control to a respective subset of the reference controls using the supervised natural language processing machine learning model based at least on the scores.

Abstract: Technologies relating to model interpretation are described herein. A text classifier is provided with input text and assigns a class to the input text from amongst several possible classes. Based upon the class assigned to the input text by the text classifier, a class profile of a centroidal classifier is selected, where the class profile is constructed based upon numerous input texts to which the text classifier has previously assigned the class. Based upon the selection of the class profile, information that is indicative of operation of the text classifier with respect to the text classifier assigning the class to the input text is output, where the information includes an exemplar text sequence.

Abstract: A computer implemented method of identifying rare events includes receiving information representative of an event. A first machine learning network trained to classify events in a majority class is executed on the received information representative of the event. A second machine learning network trained to classify events in a minority class is executed on the received information representative of the event. The first and second machine learning networks may be executed in parallel or serially. The classifications of the first and second machine learning networks are then combined to predict the class of the information representative of the event.

Abstract: Technologies related to predicting whether a requested change (deployment) in a cloud computing environment will fail are described herein. An exposomic feature value is computed based upon a time series of risk values, where the risk values represent risk of failure over several historic time intervals. A probabilistic model computes a likelihood that the requested deployment will fail during implementation of the requested deployment based upon the exposomic feature value and a contextual feature value, and a notification is transmitted to a computing device of a change manager to allow the change manager to take remedial action.

Abstract: Described herein are technologies pertaining to identifying and applying association rules in connection with identifying a root cause of a problem in a computing system. The association rules are constrained such that one side of the association rules is unidimensional. Upon an incident report being received, association rules that are relevant to the incident report are identified and ranked, where a top threshold number of association rules is employed to identify a potential root cause of an incident represented by the incident report.

Abstract: Technologies related to predicting whether a requested change (deployment) in a cloud computing environment will fail are described herein. An exposomic feature value is computed based upon a time series of risk values, where the risk values represent risk of failure over several historic time intervals. A probabilistic model computes a likelihood that the requested deployment will fail during implementation of the requested deployment based upon the exposomic feature value and a contextual feature value, and a notification is transmitted to a computing device of a change manager to allow the change manager to take remedial action.

Abstract: A method comprises inputting used oil analysis data to a pre-trained predictive model, the used oil analysis data including values quantifying a plurality of chemical components measured in a sample of used oil taken from an engine under analysis, determining a probability of at least one fail code with the pre-trained predictive model in response to the used oil analysis data, the at least one fail code corresponding to one of a plurality of predetermined engine failure types, providing the at least one fail code and the probability of the at least one fail code to an expert system, performing with the expert system a root cause analysis of the at least one fail code determine a root cause indicating a preventative maintenance action, and performing the predictive maintenance action on the engine under analysis.

Abstract: Technologies relating to model interpretation are described herein. A text classifier is provided with input text and assigns a class to the input text from amongst several possible classes. Based upon the class assigned to the input text by the text classifier, a class profile of a centroidal classifier is selected, where the class profile is constructed based upon numerous input texts to which the text classifier has previously assigned the class. Based upon the selection of the class profile, information that is indicative of operation of the text classifier with respect to the text classifier assigning the class to the input text is output, where the information includes an exemplar text sequence.

Abstract: A method, system, and computer program product is provided for the determination of a single delivery status of a message sent to multiple recipients which also allows the message to be transmitted or transferred through multiple message protocols, such as Extended Simple Message Transfer Protocol (ESMTP), Messaging Application Programming Interface (MAPI), and Vendor Independent Messaging (VIM). A sender generates an original message that is intended to be sent to multiple recipients. When a delivery status notification is received from a recipient, the delivery status notification contains a protocol-specific delivery status code. The protocol-specific status codes of multiple messaging protocols are mapped to a protocol-neutral set of status codes that can be commonly applied to any given messaging protocol.