Adobe, Inc.

Christopher John Challis

Wei Zhang

Aishwarya Asesh

The present technology provides for facilitating efficient identification of relevant metrics. In one embodiment, a set of candidate metrics for which to determine relevance to a user is identified. For each candidate metric, a set of distribution parameters is determined, including a first distribution parameter based on implicit positive feedback associated with the metric and usage data associated with the metric and a second distribution parameter based on the usage data associated with the metric. Such usage data can efficiently facilitate identifying relevance even with an absence of negative feedback. Using the set of distribution parameters, a corresponding distribution is generated. Each distribution can then be sampled to identify a relevance score for each candidate metric indicating an extent of relevance of the corresponding metric. Based on the relevance scores for each candidate metric, a candidate metric is designated as relevant to the user.

Facilitating efficient identification of relevant data

Systems and methods for facilitating updates to software programs via machine-learning techniques are disclosed. In an example, an application generates a feature vector from a textual description of a software defect by applying a topic model to the textual description. The application uses the feature vector and one or more machine-learning models configured to predict classifications and sub-classifications of the textual description. The application integrates the classifications and the sub-classifications into a final classification of the textual description that indicates a software component responsible for causing the software defect. The final classification is usable for correcting the software defect.

Software component defect prediction using classification models that generate hierarchical component classifications

Embodiments of the present technology provide systems, methods, and computer storage media for facilitating anomaly detection. In some embodiments, a prediction model is generated using a training data set. The prediction model is used to predict an expected value for a latest (current) timestamp, which is used to determine that the incoming observed data value is an anomaly. Based on the incoming observed data value determined to be the anomaly or not, a corrected data value is generated to be included in the training data set. Thereafter, the training data set having the corrected data value is used to update the prediction model for use in determining whether a subsequent observed data value is anomalous. Such a process may be performed in an iterative manner to maintain optimized training data and prediction model.

Facilitating efficient and effective anomaly detection via minimal human interaction

An anomaly analysis system generates models capable of more accurately identifying anomalies in data that contains unsatisfactory training data. The anomaly analysis system determines when data contains unsatisfactory training data. When an anomaly is detected in data using an initially selected model, and the data contains unsatisfactory training data, model reselection is performed. The reselected model analyzes the data. The reselected model is used to identify any anomalies in the data based on a data point from the data being outside of a confidence interval related to a predicted point by the reselected model corresponding to the data point.

Model reselection for accommodating unsatisfactory training data

A server monitoring methodology uses a time-series model for predicting value of a metric of a server. The model is built using initial training data that includes median values of the metric, each median value based on previously measured values of that metric, from servers of a group to which the server is being added. The methodology includes observing the value of the metric of the server, and comparing that observed value to a predicted value of the model. In response to the observed value being within an expected tolerance, the training data is updated to include the observed value; and in response to the observed value being outside the expected tolerance, the training data is updated to include a value between the observed value of the server metric and the predicted value. The model is updated using the updated training data, and eventually adapts to performance of the server.

Growing community of inventors

Alpine, UT, United States of America

Christopher John Challis