Abstract: A descriptor generation unit 81 uses a first template prepared in advance to generate a feature descriptor, which generates a feature that may affect a prediction target from a first table including a variable of the prediction target and a second table. A feature generation unit 82 generates the feature by applying the feature descriptor to the first and second tables. A feature explanation generation unit 83 generates a feature explanation about the feature descriptor or the feature on the basis of a second template. An accepting unit 84 accepts values to be assigned to the first and second templates. The descriptor generation unit 81 generates the feature descriptor by assigning the accepted values to the first template, and the feature explanation generation unit 83 generates the feature explanation by assigning the values assigned to the first template to the second template.

Abstract: A distribution system 100 includes a data management apparatus 10 and a plurality of calculators 20 that execute machine learning. The data management apparatus 10 includes a data acquisition unit 11 that acquires information regarding training data held in a memory 21 of each of the calculators 20, from the calculators 20, and a data rearrangement unit 12 that determines training data that is to be held in the memory 21 of each of the calculators 20, based on characteristics of the machine learning processes that are executed by the calculators 20, and the information acquired from the calculators.

Abstract: A learning unit 81 generates a plurality of sample groups from samples to be used for learning, and generates a plurality of prediction models while inhibiting overlapping of a sample group to be used for learning among the generated sample groups. An optimization unit 82 generates an objective function based on an explained variable predicted by the prediction model and based on a constraint condition for optimization, and optimizes a generated objective function. An evaluation unit 83 evaluates an optimization result by using a sample group that has not been used in learning of a prediction model used for generating an objective function targeted for the optimization.

Abstract: A table acquiring means 381 acquires a first table including prediction objects and first attributes, and a second table including second attributes. A receiving means 382 receives a similarity function and condition for similarity used to calculate the similarity between the first attribute and the second attribute. A feature generating means 383 generates feature candidates able to affect a prediction object using a combination condition for combining a record in the first table including the value of a first attribute satisfying the condition with a record in the second table including the value of a second attribute satisfying the similarity calculated with the value of the first attribute and the value of the second attribute using the similarity function, and using a reduction method for a plurality of records in the second table and a reduction condition represented by the column to be aggregated. A feature selecting means 384 selects an optimum feature for the prediction from the feature candidates.

Abstract: A computational resource management apparatus is for managing a cluster system that executes a plurality of tasks. The computational resource management apparatus includes a condition specification unit that specifies a relationship between computational resources of the cluster system and computation time, a dependency relationship between tasks, and an execution time limit of each task, and a scheduling unit that determines, for each task, an execution sequence and computational resources to be allocated from among the computational resources of the cluster system, based on the relationship between the computational resources and computation time and the dependency relationship that are specified, such that the execution time limit is met.

Abstract: A prediction data input unit 91 inputs prediction data that is one or more explanatory variables that are information likely to affect future sales. An exposure pattern generation unit 92 generates an exposure pattern which is an explanatory variable indicating the content of a commercial message scheduled to be performed during a period from predicted time to future prediction target time. A component determination unit 93 determines the component used for predicting the sales, on the basis of a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure, gating functions for determining a branch direction in the nodes of the hierarchical latent structure, and the prediction data and the exposure pattern.

Abstract: An analysis process receiving unit 282 receives creation of an analysis process which is a series of processing operations for analyzing data using a column name defined by a schema to be applied to a table. A schema/analysis process storing unit 283 stores information in which the received analysis process is associated with a schema that can be applied to the analysis process. When selection of an analysis process has been received from the user, a table retrieval unit 284 outputs a list of tables used by the received analysis process on the basis of information stored in a table/schema storing unit and information stored in a schema/analysis process storing unit 283. An analysis process executing unit 285 receives selection of a table from the outputted list of tables, and executes the selected analysis process on the received table.

Abstract: An analysis process receiving unit 182 receives creation of an analysis process which is a series of processing operations for analyzing data using a column name defined by a schema to be applied to a table. A schema/analysis process storing unit 183 stores information in which the received analysis process is associated with a schema that can be applied to the analysis process. When selection of a table has been received from the user, an analysis process retrieval unit 184 outputs a list of tables used by the received analysis process on the basis of information stored in a table/schema storing unit and information stored in a schema/analysis process storing unit 183. An analysis process executing unit 185 receives selection of an analysis process from the outputted list, and executes the selected analysis process on the received table.

Abstract: A learning unit 81 generates a plurality of sample groups from samples to be used for learning, and generates a plurality of prediction models while inhibiting overlapping of a sample group to be used for learning among the generated sample groups. An optimization unit 82 generates an objective function based on an explained variable predicted by the prediction model and based on a constraint condition for optimization, and optimizes a generated objective function. An evaluation unit 83 evaluates an optimization result by using a sample group that has not been used in learning of a prediction model used for generating an objective function targeted for the optimization.

Abstract: A computational resource management apparatus is for managing a cluster system that executes a plurality of tasks. The computational resource management apparatus includes a condition specification unit that specifies a relationship between computational resources of the cluster system and computation time, a dependency relationship between tasks, and an execution time limit of each task, and a scheduling unit that determines, for each task, an execution sequence and computational resources to be allocated from among the computational resources of the cluster system, based on the relationship between the computational resources and computation time and the dependency relationship that are specified, such that the execution time limit is met.

Abstract: A computational resource management device uses a measured value of an execution time of data processing, a measured value of a resource amount, and a feature of input data as training data to learn a model indicating a relationship between the execution time and the resource. The device inputs, into the model, a feature of data scheduled to be input to calculate an estimated value of the execution time of the scheduled data processing, and uses the estimated value of the execution time, a variation index indicating variation in the estimated value of the execution time, and distribution of estimated residuals to calculate a resource amount required in the scheduled data processing. The device creates an execution plan of the scheduled data processing, based on the estimated value of the execution time, the variation index, the distribution of estimated residuals, and the calculated resource amount.

Abstract: An apparatus that extracts an explanatory variable used as a condition from a classification model classified by the condition for selecting a component used for prediction, displays the explanatory variable in association with any of dimensional axes of a multi-dimensional space in which a prediction value is displayed, specifies the component that corresponds to a position in the multi-dimensional space specified by each of the explanatory variables associated with the dimensional axis, displays the prediction value calculated based on the specified component, on the same position and displays the multi-dimensional space that corresponds to the position in which the prediction value is displayed, in a mode that corresponds to the component used for calculating the prediction value.

Abstract: A learning unit 81 generates a plurality of sample groups from samples used for learning, each of the sample groups containing at least one of samples not contained in the other sample groups, and generates a plurality of prediction models using each of the generated sample groups. An optimization unit 82 generates objective functions, represented by the sum of a plurality of functions, on the basis of explained variables predicted by the prediction models and constraints for optimization, and optimizes the generated objective functions. An evaluation unit 83 evaluates a result of the optimization for each of the objective functions.

Abstract: A table storage unit 81 stores a first table including an objective variable and a second table different in granularity from the first table. A descriptor creation unit 82 creates a feature descriptor for generating a feature which is a variable that can influence the objective variable, from the first table and the second table. The descriptor creation unit 82 creates a plurality of feature descriptors, each by generating a combination of a mapping condition element indicating a mapping condition for rows in the first table and the second table and a reduction method element indicating a reduction method for reducing, for each objective variable, data of each column included in the second table.

Abstract: A classifier 81 classifies target data into a cluster on the basis of a mixture model defined using two different types of variables that indicate features of the target data. In this classification, the classifier 81 classifies the target data into a cluster on the basis of a mixture model in which a mixing ratio of the mixture model is represented by a function of a first variable and in which the element distribution of the clusters into which the target data is classified is represented by a function of a second variable.

Abstract: A descriptor generation unit 81 uses a first template prepared in advance to generate a feature descriptor, which generates a feature that may affect a prediction target from a first table including a variable of the prediction target and a second table. A feature generation unit 82 generates the feature by applying the feature descriptor to the first and second tables. A feature explanation generation unit 83 generates a feature explanation about the feature descriptor or the feature on the basis of a second template. An accepting unit 84 accepts values to be assigned to the first and second templates. The descriptor generation unit 81 generates the feature descriptor by assigning the accepted values to the first template, and the feature explanation generation unit 83 generates the feature explanation by assigning the values assigned to the first template to the second template.

Abstract: An accepting unit 71 accepts a feature descriptor, which generates a feature, i.e. a variable that may affect a prediction target, from a first table including a variable of the prediction target and a second table. An extraction unit 72 extracts, from the feature descriptor, table information indicating a name of the second table, joint information indicating key columns when joining the first table and the second table, and aggregation information indicating an aggregation operation to be performed on a plurality of rows in the second table and a column as a target of the aggregation operation. A feature explanation generation unit 73 assigns the extracted information to a feature explanation template to generate a feature explanation of the feature, which is obtained by applying the feature generator to the first table and the second table.

Abstract: A table acquiring means 181 acquires a first table including prediction targets and first geographic attributes, and a second table including second geographic attributes. A receiving means 182 receives geographic relationships and degrees of geographic relationships. A combination condition generating means 183 generates a combination condition for combining a record included in the first table with a record included in the second table so that the relationship between the value of a first geographic attribute and the value of a second geographic attribute satisfies the degree of geographic relationship.

Abstract: A table acquiring means 381 acquires a first table including prediction objects and first attributes, and a second table including second attributes. A receiving means 382 receives a similarity function and condition for similarity used to calculate the similarity between the first attribute and the second attribute. A feature generating means 383 generates feature candidates able to affect a prediction object using a combination condition for combining a record in the first table including the value of a first attribute satisfying the condition with a record in the second table including the value of a second attribute satisfying the similarity calculated with the value of the first attribute and the value of the second attribute using the similarity function, and using a reduction method for a plurality of records in the second table and a reduction condition represented by the column to be aggregated. A feature selecting means 384 selects an optimum feature for the prediction from the feature candidates.

Abstract: A distribution system 100 includes a data management apparatus 10 and a plurality of calculators 20 that execute machine learning. The data management apparatus 10 includes a data acquisition unit 11 that acquires information regarding training data held in a memory 21 of each of the calculators 20, from the calculators 20, and a data rearrangement unit 12 that determines training data that is to be held in the memory 21 of each of the calculators 20, based on characteristics of the machine learning processes that are executed by the calculators 20, and the information acquired from the calculators.