Abstract: In an approach to risk prediction for bug-introducing changes, a computer retrieves one or more historic pull requests. A computer determines a unique file linking for each file included in the historic pull requests. A computer generates a file risk dataset. A computer performs chronological partitioning on the file risk dataset. A computer determines bug-introducing changes in the file risk dataset. A computer computes a collaborative file association between two or more of the files in the file risk dataset. A computer labels each of the files in the file risk dataset with an associated risk of introducing a bug. A computer generates a labelled file risk inducing ground truth dataset. A computer inputs the labelled file risk inducing ground truth dataset to a file risk prediction model. A computer extracts pull request features from the historic pull requests. A computer generates a pull request risk prediction model.

Abstract: In an approach to risk prediction for bug-introducing changes, a computer retrieves one or more historic pull requests. A computer determines a unique file linking for each file included in the historic pull requests. A computer generates a file risk dataset. A computer performs chronological partitioning on the file risk dataset. A computer determines bug-introducing changes in the file risk dataset. A computer computes a collaborative file association between two or more of the files in the file risk dataset. A computer labels each of the files in the file risk dataset with an associated risk of introducing a bug. A computer generates a labelled file risk inducing ground truth dataset. A computer inputs the labelled file risk inducing ground truth dataset to a file risk prediction model. A computer extracts pull request features from the historic pull requests. A computer generates a pull request risk prediction model.

Abstract: An approach for generating actionable explanations of change request classifications may be presented. A model may generate features associated with a change request may be disclosed. The model may be trained with historical change requests that have been labeled risky or not risky. The change request may be classified as risky or not risky. Candidate historical change requests with the same classification as the change request and occupying similar feature space as the change request may be identified from a historical change request repository. One or more features which had the most significant impact on the classification may be identified. A candidate historical change request with at least one significant feature impacting classification may be identified.

Abstract: A method and a system for model training are provided. The method can include training a first classifier, a second classifier, and a third classifier with subsets of a labeled dataset. The method can also include predicting a pseudo labeled dataset from an unlabeled dataset using the first classifier, the second classifier, and the third classifier. The method further includes assigning a role to the first classifier, to the second classifier, and to the third classifier. The method can further include selecting a teaching sample dataset from the pseudo labeled dataset based on the role assigned to the third classifier, wherein the third classifier is assigned a role of a student. The method can also include retraining the third classifier with the teaching sample dataset in conjunction with a subset of the labeled dataset.

Abstract: A method, system, and a computer program product automatically select training data for updating a model by applying human-annotated training data to a model to generate results that are evaluated to identify correct case results and false case results that are categorized into error type categories for use in building error models corresponding to the error type categories, where each error model is built from at least failed case results belonging to a corresponding error type, and where unlabeled data samples are applied to each error model to compute an error likelihood for each unlabeled data sample with respect to each error type category, thereby enabling the selection and display of unlabeled data samples for annotation by a subject matter expert based on a computed error likelihood for the one or more unlabeled data samples in a specified error type category meeting or exceeding an error threshold requirement.

Abstract: A method, system, and a computer program product automatically select training data for updating a model by applying human-annotated training data to a model to generate results that are evaluated to identify correct case results and false case results that are categorized into error type categories for use in building error models corresponding to the error type categories, where each error model is built from at least failed case results belonging to a corresponding error type, and where unlabeled data samples are applied to each error model to compute an error likelihood for each unlabeled data sample with respect to each error type category, thereby enabling the selection and display of unlabeled data samples for annotation by a subject matter expert based on a computed error likelihood for the one or more unlabeled data samples in a specified error type category meeting or exceeding an error threshold requirement.

Abstract: A method and a system for model training are provided. The method can include training a first classifier, a second classifier, and a third classifier with subsets of a labeled dataset. The method can also include predicting a pseudo labeled dataset from an unlabeled dataset using the first classifier, the second classifier, and the third classifier. The method further includes assigning a role to the first classifier, to the second classifier, and to the third classifier. The method can further include selecting a teaching sample dataset from the pseudo labeled dataset based on the role assigned to the third classifier, wherein the third classifier is assigned a role of a student. The method can also include retraining the third classifier with the teaching sample dataset in conjunction with a subset of the labeled dataset.

Abstract: Embodiments of a system for determining personal attributes based on public interaction data are illustrated. In one embodiment, the system employs a process for predicting personal attributes based on public interaction data by constructing matrices based on user interactions drawn from public posts on a social media website. The process may further learn a compact representation for a plurality of users based on public posts using the matrices, extract the compact representation of one or more users that have been labeled, and apply a classifier to learn about a particular personal attribute. Through this, a prediction of personal attributes of users that have not been labeled may be obtained.

Abstract: Embodiments of a system for determining personal attributes based on public interaction data are illustrated. In one embodiment, the system employs a process for predicting personal attributes based on public interaction data by constructing matrices based on user interactions drawn from public posts on a social media website. The process may further learn a compact representation for a plurality of users based on public posts using the matrices, extract the compact representation of one or more users that have been labeled, and apply a classifier to learn about a particular personal attribute. Through this, a prediction of personal attributes of users that have not been labeled may be obtained.