Abstract: In an example embodiment, a solution that automatically predicts an industry for a candidate company is provided. An existing industry classifier is trained using a first machine learning algorithm, the first machine learning algorithm taking as input first training data and existing industries listed in an industry taxonomy. A new industry classifier is trained using a second machine learning algorithm, the second machine learning algorithm taking as input second training data and new industries listed in an industry taxonomy. Then the candidate company is fed into the existing industry classifier, producing one or more predicted existing industries corresponding to the candidate company. The candidate company is also fed into the new industry classifier, producing one or more predicted new industries corresponding to the candidate company. One or more final predicted industries are selected from among the one or more predicted existing industries and the one or more predicted new industries.

Abstract: A diagnosis support apparatus which supports diagnosis based on information associated with a diagnosis name in advance is provided. In the diagnosis support apparatus, an acquisition unit acquires the diagnosis name set by a user. A providing unit provides negative information for the diagnosis name set by the user based on the information. With the above arrangement, the diagnosis support apparatus selects and presents information influencing the diagnosis name expected by the user, thereby efficiently presenting information required by the user.

Abstract: The present invention envisages a system and method for automating the generation of business decision analytic models. The system uses a plurality of predictor variables stored in a plurality of data sets, to automatically create a business decision analytic model. The system includes a processor configured to process the data sets and determine the total number of records present in each of the data sets and the number of columns containing only numerical values. The processor selects a column containing only numerical values, from a dataset under consideration, and counts the number of unique numerical values in the selected column, and the total number of records present in the selected column. The two counts are compared and the selected column is transformed using a non-linear transformation to obtain a column of transformed values. The transformed values and corresponding time stamps are utilized for the purpose of model generation.

Abstract: A mechanism is provided in a data processing system for automatically generating question and answer pairs for training a question answering system for a given domain. The mechanism receives user input of question text for a question to be submitted to a question answering system in a user interface. The mechanism determines a question strength score for the question text. The question strength score represents a likelihood the question text will result in a correct answer with high confidence. The mechanism presents a graphical representation of the question strength score in the user interface.

Abstract: Hybrid feature selection methods include methods of creating a predictive model for valve performance in a fleet of aircraft. Methods include qualifying a qualification dataset of valve-related parameters calculated from data collected during a first series of flights at least before and after a non-performance event of a valve. Methods include receiving a qualified selection of the valve-related parameters and verifying a verification dataset of the qualified selection of the valve-related parameters calculated from data collected during a second series of flights. Methods include receiving a set of verified and qualified valve-related parameters and building a predictive model for valve non-performance with a training dataset of the verified and qualified valve-related parameters calculated from data collected during additional flights of the fleet.

Abstract: A computer implemented system for automating the generation of an analytic model includes a processor configured to process a plurality of data sets. Each data set includes values for a plurality of variables. A time-stamping module is configured to derive values for a plurality of elapsed-time variables for each data set, and the plurality of variables and plurality of elapsed-time variables are included in a plurality of model variables. A model generator is configured to create a plurality of comparison analytic models each based on a different subset of model variables. Each comparison analytic model is configured to operate on new data sets associated with current leads, and to output a likelihood of successfully closing an associated transaction. A model testing module is configured to select an operational analytic model from among the comparison analytic models based on a quality metric.

Abstract: A method and system of inferential-based communications applies two sets of values, whereby the first set of values are determined from inferences of the relevancy of textual elements with respect to text-based content and the second set of values are determined from behavioral-based inferences with respect to topics, so as to select appropriate words to be included in communications that are generated for delivery to a user. The inferences that are with respect to text-based content may be determined by applying analytic methods such as Bayesian or statistical learning-based methods. The values that are determined from behavioral-based inferences with respect to topics may correspond to inferences of interest and/or expertise. Words in the communications may be selected and/or arranged in accordance with syntactical rules and may reference elements of the text-based content and/or behavioral inferences.

Abstract: Presenting ancestral origin information, comprising: receiving a request to display ancestry data of an individual; obtaining ancestry composition information of the individual, the ancestry composition information including information pertaining to a proportion of the individual's genotype data that is deemed to correspond to a specific ancestry; and presenting the ancestry composition information to be displayed.

Abstract: A method for touch classification includes obtaining frame data representative of a plurality of frames captured by a touch-sensitive device, analyzing the frame data to define a respective blob in each frame of the plurality of frames, the blobs being indicative of a touch event, computing a plurality of feature sets for the touch event, each feature set specifying properties of the respective blob in each frame of the plurality of frames, and determining a type of the touch event via machine learning classification configured to provide multiple non-bimodal classification scores based on the plurality of feature sets for the plurality of frames, each non-bimodal classification score being indicative of an ambiguity level in the machine learning classification.

Abstract: A computer implemented system for automating the generation of an analytic model includes a processor configured to process a plurality of data sets. Each data set includes values for a plurality of variables. A time-stamping module is configured to derive values for a plurality of elapsed-time variables for each data set, and the plurality of variables and plurality of elapsed-time variables are included in a plurality of model variables. A model generator is configured to create a plurality of comparison analytic models each based on a different subset of model variables. Each comparison analytic model is configured to operate on new data sets associated with current opportunities, and to output a likelihood of successfully closing each current opportunity. A model testing module is configured to select an operational analytic model from among the comparison analytic models based on a quality metric.

Abstract: A variational autoencoder (VAE) neural network system, comprising an encoder neural network to encode an input data item to define a posterior distribution for a set of latent variables, and a decoder neural network to generate an output data item representing values of a set of latent variables sampled from the posterior distribution. The system is configured for training with an objective function including a term dependent on a difference between the posterior distribution and a prior distribution. The prior and posterior distributions are arranged so that they cannot be matched to one another. The VAE system may be used for compressing and decompressing data.

Abstract: Methods and devices for retrospectively assessing continuous monitoring reference pattern data to determine a risk of a patient glucose level measurement taken in at least one data segment being outside a predetermined range. The methods and devices can include executing an algorithm to compare risk scores derived from reference pattern data in a currently collected data segment with risk scores of previously stored reference pattern data of previously collected data segments for a patient for assessing risk.

Abstract: Methods and systems for pharmacy modeling are described. The risk adjusted pharmacy predictive model is created from member data, claims data, and population data. This model can be used to compare the actual pharmacy performance to an expected actual pharmacy performance value, which can be used to identify pharmacies at risk or not performing to an acceptable level. The model can be used for adherence and generic drug utilization ratings of pharmacies. The pharmacy can be judged on a therapy class by therapy class basis with factors that reflect the demographic, socio-economic, location, benefits attributes, etc. that actually affect the performance of the pharmacy and may assist in determining the quality of care by a pharmacy.

Abstract: Version vector-based rules are used to facilitate asynchronous execution of machine learning algorithms. The method uses version vector based rule to generate aggregated parameters and determine when to return the parameters. The method also includes coordinating the versions of aggregated parameter sets among all the parameter servers. This allows to broadcast to enforce the version consistency; generate parameter sets in an on-demand manner to facilitate version control. Furthermore the method includes enhancing the version consistency at the learner's side and resolving the inconsistent version when mismatching versions are detected.

Abstract: Ancestry deconvolution includes obtaining unphased genotype data of an individual; phasing, using one or more processors, the unphased genotype data to generate phased haplotype data; using a learning machine to classify portions of the phased haplotype data as corresponding to specific ancestries respectively and generate initial classification results; and correcting errors in the initial classification results to generate modified classification results.

Abstract: Version vector-based rules are used to facilitate asynchronous execution of machine learning algorithms. The method uses version vector based rule to generate aggregated parameters and determine when to return the parameters. The method also includes coordinating the versions of aggregated parameter sets among all the parameter servers. This allows to broadcast to enforce the version consistency; generate parameter sets in an on-demand manner to facilitate version control. Furthermore the method includes enhancing the version consistency at the learner's side and resolving the inconsistent version when mismatching versions are detected.

Abstract: The disclosure generally describes computer-implemented methods, software, and systems for modeling and deploying decision services. One computer-implemented method includes creating a connection between a decision service manager and a managed system, establishing a signature of a decision service, developing, using at least one computer, the decision service based upon the established signature of the decision service, performing a deployment readiness check, transferring generated code implementing the decision service to the managed system upon a determination that the deployment readiness check was successful, inserting the generated code into the managed system, and retrieving a deployment status from the managed system.

Abstract: Example embodiments relate to a network-based ontology curation system employed for receiving a request to view a data object, curating an ontology associated with the data object on-the-fly based on attributes of the request that include device and user characteristics.

Abstract: A system and method for learning and/or optimizing processes related to semiconductor manufacturing is provided. A learning component generates a set of candidate process models based on process data associated with one or more fabrication tools. The learning component also selects a particular process model from the set of candidate process models that is associated with lowest error. An optimization component generates a set of candidate solutions associated with the particular process model. The optimization component also selects a particular solution from the set of candidate solutions based on a target output value and an output value associated with the particular solution.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting answers to questions about documents. One of the methods includes receiving a document comprising a plurality of document tokens; receiving a question associated with the document, the question comprising a plurality of question tokens; processing the document tokens and the question tokens using a reader neural network to generate a joint numeric representation of the document and the question; and selecting, from the plurality of document tokens, an answer to the question using the joint numeric representation of the document and the question.