Abstract: Embodiments for implementing enhanced ensemble model diversity and learning by a processor. One or more data sets may be created by combining one or more clusters of data points of a minority class with selected data points of a majority class. One or more ensemble models may be created from the one or more data sets using a supervised machine learning operation. An occurrence of an event may be predicted using the one or more ensemble models.

Abstract: Embodiments for implementing enhanced ensemble model diversity and learning by a processor. One or more data sets may be created by combining one or more clusters of data points of a minority class with selected data points of a majority class. One or more ensemble models may be created from the one or more data sets using a supervised machine learning operation. An occurrence of an event may be predicted using the one or more ensemble models.

Abstract: An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.

Abstract: An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.

Abstract: An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.

Abstract: An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.

Abstract: An automated outlier detection system implements an unsupervised set of processes to determine feature subspaces from a dataset; determine candidate exploratory actions, where each candidate exploratory action is a specific combination of a feature subspace and a parameterized instance of an outlier detection algorithm; and identify a set of optimal exploratory actions to recommend for execution on the dataset from among the candidate exploratory actions. Outlier scores obtained as a result of execution of the set of optimal exploratory actions are processed to obtain one or more outlier views such that each outlier view represents a consistent characterization of outliers by each optimal exploratory action corresponding to that outlier view.

Abstract: A method and system for detecting an event from a social stream. The method includes the steps of: receiving a social stream from a social network, where the social stream includes at least one object and the object includes a text, sender information of the text, and recipient information of the text; assigning said object to a cluster based on a similarity value between the object and the clusters; monitoring changes in at least one of the clusters; and triggering an alarm when the changes in at least one of the clusters exceed a first threshold value, where at least one of the steps is carried out using a computer device.

Abstract: A method for classifying objects in a graph data stream, including receiving a training stream of graph data, the training stream including a plurality of objects along with class labels that are associated with each of the objects, first determining discriminating sets of edges in the training stream for the class labels, wherein a discriminating set of edges is one that is indicative of the object that contains these edges having a given class label, receiving an incoming data stream of the graph data, wherein class labels have not yet been assigned to objects in the incoming data stream, second determining, based on the discriminating sets of edges, class labels that are associated with the objects in the incoming data stream; and outputting to an information repository object class label pairs based on the second determining.

Abstract: A method and system for detecting an event from a social stream. The method includes the steps of: receiving a social stream from a social network, where the social stream includes at least one object and the object includes a text, sender information of the text, and recipient information of the text; assigning said object to a cluster based on a similarity value between the object and the clusters; monitoring changes in at least one of the clusters; and triggering an alarm when the changes in at least one of the clusters exceed a first threshold value, where at least one of the steps is carried out using a computer device.

Abstract: In a method for representing a text document with a graphical model, a document including a plurality of ordered words is received and a graph data structure for the document is created. The graph data structure includes a plurality of nodes and edges, with each node representing a distinct word in the document and each edge identifying a number of times two nodes occur within a predetermined distance from each other. The graph data structure is stored in an information repository.

Abstract: A method for classifying objects in a graph data stream, including receiving a training stream of graph data, the training stream including a plurality of objects along with class labels that are associated with each of the objects, first determining discriminating sets of edges in the training stream for the class labels, wherein a discriminating set of edges is one that is indicative of the object that contains these edges having a given class label, receiving an incoming data stream of the graph data, wherein class labels have not yet been assigned to objects in the incoming data stream, second determining, based on the discriminating sets of edges, class labels that are associated with the objects in the incoming data stream; and outputting to an information repository object class label pairs based on the second determining.

Abstract: Uncertain data is classified by constructing an error adjusted probability density estimate for the data, and applying a subspace exploration process to the probability density estimate to classify the data.

Abstract: In a method for representing a text document with a graphical model, a document including a plurality of ordered words is received and a graph data structure for the document is created. The graph data structure includes a plurality of nodes and edges, with each node representing a distinct word in the document and each edge identifying a number of times two nodes occur within a predetermined distance from each other. The graph data structure is stored in an information repository.

Abstract: A system and method for resource adaptive classification of data streams. Embodiments of systems and methods provide classifying data received in a computer, including discretizing the received data, constructing an intermediate data structure from said received data as training instances, performing subspace sampling on said received data as test instances and adaptively classifying said received data based on statistics of said subspace sampling.

Abstract: Privacy in data mining of sparse high dimensional data records is preserved by transforming the data records into anonymized data records. This transformation involves creating a sketch-based private representation of each data record, each data record containing only a small number of non-zero attribute value in relation to the high dimensionality of the data records.

Abstract: Systems and methods for providing density-based traffic generation. Data are clustered to create partitions, and transforms of clustered data are constructed in a transformed space. Data points are generated via employing grid discretization in the transformed space, and density estimates of the generated data points are employed to generate synthetic pseudo-points.

Abstract: Uncertain data is classified by constructing an error adjusted probability density estimate for the data, and applying a subspace exploration process to the probability density estimate to classify the data.

Abstract: Privacy in data mining of sparse high dimensional data records is preserved by transforming the data records into anonymized data records. This transformation involves creating a sketch-based private representation of each data record, each data record containing only a small number of non-zero attribute value in relation to the high dimensionality of the data records.

Abstract: Methods and apparatus for generating at least one output data set from at least one input data set for use in association with a data mining process are provided. First, data statistics are constructed from the at least one input data set. Then, an output data set is generated from the data statistics. The output data set differs from the input data set but maintains one or more correlations from within the input data set. The correlations may be the inherent correlations between different dimensions of a multidimensional input data set. A significant amount of information from the input data set may be hidden so that the privacy level of the data mining process may be increased.