Abstract: A method, computer system, and a computer program product for generating a custom corpus is provided. The present invention may include generating a domain graph. The present invention may also include gathering seed data based on the generated domain graph. The present invention may then include identifying domain related data based on the gathered seed data. The present invention may further include querying the domain related data. The present invention may also include creating word embeddings for the domain related data. The present invention may then include evaluating the domain related data.

Abstract: A computer-implemented method for providing interpretable predictions from a machine learning model includes receiving a data structure that represents a hierarchical structure of a set of features (X) used by one or more predictive models to generate a set of predictions (Y). An interpretability model is built corresponding to the predictive models, by assigning an interpretability to each prediction Yi based on the hierarchical structure. Assigning the interpretability includes decomposing X into a plurality of partitions Xj using the hierarchical structure, wherein X=U1NXj, N being the number of partitions. Further, each partition is decomposed into a plurality of sub-partitions using the hierarchical structure until atomic sub-partitions are obtained. A score is computed for each partition as a function of the predicted scores of the sub-partitions, wherein the predicted scores represent interactions between the sub-partitions. Further, an interpretation of a prediction is outputted.

Abstract: A system, method and computer program product, which given in input a question in natural language format, delivers personalized insights related to the answer. Personalized insights are selected among candidate insights mined from the data and ranked based on closeness to (mined) user-preference, relevance to the question, and surprise factor. Two core components include: Question analysis and meaningful insight look up and Multi-dimensional insight ranking. The Question analysis and meaningful insights lookup module performs a semantic analysis of the questions and, uses techniques including “templates” to build new questions which could uncover insights from the data. The Multi-dimensional insight ranking module takes in input a list of insights returned from Question analysis and meaningful insights lookup and rank such insights based on such factors as: relevance to the query, surprise factor, and user preferences.

Abstract: A system, method and program product for analyzing product preferences and providing trend analysis for a gathering of individuals at an event. An infrastructure is disclosed having a system for setting up and managing an event; a system for registering users physically attending the event; a system for registering items associated with the users and storing event-user-item (EUI) information in an EUI database; and an analysis system for analyzing EUI information to provide item preferences and trend analysis.

Abstract: The disclosure relates to extraction of rationales for studied outcome. A method comprises: grouping features as expert to align with a set of operating practices; generating interpretable features using operating rules, combining with statistical dependence analysis to bin selected features to generate favorite practice actions; grouping features as expert that combine a subset of the interpretable features to align with a set of operating practices.

Abstract: A computer-implemented method for providing interpretable predictions from a machine learning model includes receiving a data structure that represents a hierarchical structure of a set of features (X) used by one or more predictive models to generate a set of predictions (Y). An interpretability model is built corresponding to the predictive models, by assigning an interpretability to each prediction Yi based on the hierarchical structure. Assigning the interpretability includes decomposing X into a plurality of partitions Xj using the hierarchical structure, wherein X=U1NXj, N being the number of partitions. Further, each partition is decomposed into a plurality of sub-partitions using the hierarchical structure until atomic sub-partitions are obtained. A score is computed for each partition as a function of the predicted scores of the sub-partitions, wherein the predicted scores represent interactions between the sub-partitions. Further, an interpretation of a prediction is outputted.

Abstract: A system, method and program product for analyzing product preferences and providing trend analysis for a gathering of individuals at an event. An infrastructure is disclosed having a system for setting up and managing an event; a system for registering users physically attending the event; a system for registering items associated with the users and storing event-user-item (EUI) information in an EUI database; and an analysis system for analyzing EUI information to provide item preferences and trend analysis.

Abstract: A method, computer system, and a computer program product for generating a custom corpus is provided. The present invention may include generating a domain graph. The present invention may also include gathering seed data based on the generated domain graph. The present invention may then include identifying domain related data based on the gathered seed data. The present invention may further include querying the domain related data. The present invention may also include creating word embeddings for the domain related data. The present invention may then include evaluating the domain related data.

Abstract: A system, method and program product for analyzing product preferences and providing trend analysis for a gathering of individuals at an event. An infrastructure is disclosed having a system for setting up and managing an event; a system for registering users physically attending the event; a system for registering items associated with the users and storing event-user-item (EUI) information in an EUI database; and an analysis system for analyzing EUI information to provide item preferences and trend analysis.

Abstract: Receiving a first model associated with a user, a generic model of a generic domain, and a specific domain having an associated domain-specific corpus. A first set of query terms based on elements of the first model, and a second set of query terms based on elements of the generic model, are determined. A third set of query terms is generated based on the first and second sets of query terms. The domain specific corpus is queried using the third set of query terms, and a domain specific model is generated based on results of the querying.

Abstract: A method of processing construction documentation includes receiving, as input data into a processor of a computer, a document directed to a specific construction project as input data. The processor extracts location and context information from the document. The location information defines locations relevant to the specific construction project and the context information comprises text extracted from image data of the document.

Abstract: The disclosure relates to extraction of rationales for studied outcome. A method comprises: grouping features as expert to align with a set of operating practices; generating interpretable features using operating rules, combining with statistical dependence analysis to bin selected features to generate favorite practice actions; grouping features as expert that combine a subset of the interpretable features to align with a set of operating practices.

Abstract: An aspect of the disclosure includes a method, a system and a computer program product for matching a participant with an interest group at a venue. The system including computer inputs that receive signals identifying locations of participants in a venue having sessions, the computer inputs identifying a session location for each participant. An aggregator is coupled the computer inputs and determines interests of each participant by aggregating common session characteristics with participant behavioral characteristics and ranking a degree of interests for each participant. A matcher is coupled to the aggregator receives interest group ranked lists for each interest group, the matcher further matching the interest group to the participant by matching the degree of interests for each participant to the interest group interests. A signal output is coupled to the matcher and transmits an output signal to a representative based on a relevancy parameter being above a threshold.

Abstract: A system, method and computer program product, which given in input a question in natural language format, delivers personalized insights related to the answer. Personalized insights are selected among candidate insights mined from the data and ranked based on closeness to (mined) user-preference, relevance to the question, and surprise factor. Two core components include: Question analysis and meaningful insight look up and Multi-dimensional insight ranking. The Question analysis and meaningful insights lookup module performs a semantic analysis of the questions and, uses techniques including “templates” to build new questions which could uncover insights from the data. The Multi-dimensional insight ranking module takes in input a list of insights returned from Question analysis and meaningful insights lookup and rank such insights based on such factors as: relevance to the query, surprise factor, and user preferences.

Abstract: Aspects of the present invention include a method, system and computer program product. The method includes determining, by the processor, an optimal bid price for each one of a plurality of campaigns in each one of a plurality of online real time bidding auctions. The method also includes determining, by the processor, a winning function for bids placed for campaigns in each one of a plurality of online real time bidding auctions, and determining, by the processor, a bidding function for bids placed for campaigns in each one of a plurality of online real time bidding auctions. The method also includes determining, by the processor, the optimal bid price for each one of a plurality of campaigns in each one of a plurality of online real time bidding auctions as a function of the determined winning function and the determined bidding function.

Abstract: Methods and a system are provided. A method includes extracting subsequences from a sequence of a customer journey that includes customer interactions on different channels at different times on different topics. The method further includes measuring an effectiveness of each of the subsequences based on journey success data, by applying a statistical hypothesis testing approach. The method also includes determining a contribution of each of the customer interactions for a given one of the subsequences, by applying a sequence-based journey attribution model.

Abstract: An aspect of the disclosure includes a method, a system and a computer program product for matching a participant with an interest group at a venue. The system including computer inputs that receive signals identifying locations of participants in a venue having sessions, the computer inputs identifying a session location for each participant. An aggregator is coupled the computer inputs and determines interests of each participant by aggregating common session characteristics with participant behavioral characteristics and ranking a degree of interests for each participant. A matcher is coupled to the aggregator receives interest group ranked lists for each interest group, the matcher further matching the interest group to the participant by matching the degree of interests for each participant to the interest group interests. A signal output is coupled to the matcher and transmits an output signal to a representative based on a relevancy parameter being above a threshold.

Abstract: A method for automatic placement opportunity bidding of digital advertising in a real-time advertisement exchange includes receiving a request for an ad placement opportunity from the exchange or a content publisher. The request includes information pertaining to a user who is presently viewing on-line content. Audience segments that the user belongs to are identified. An audience group is identified based on the audience segments. It is determined if a first and/or a second ad campaign of an advertiser should respond to the requests based on the identified audience group. When there is an audience conflict, it is resolved to identify one single ad campaign to respond to the placement opportunity request. The bid for the placement opportunity is submitted on behalf of the identified ad campaign.

Abstract: An aspect of the disclosure includes a method, a system and a computer program product for retargeting content to a decision making unit. The method including determining a journey stage for each of the plurality of individuals. A retargeting strategy is identified for each of the plurality of individuals, the retargeting strategy based at least in part on the journey stage for each of the plurality of individuals and a cost factor. Content data is transmitted to at least one of the plurality of individuals using retargeting based at least in part on the retargeting strategy.

Abstract: A system, method and program product for analyzing product preferences and providing trend analysis for a gathering of individuals at an event. An infrastructure is disclosed having a system for setting up and managing an event; a system for registering users physically attending the event; a system for registering items associated with the users and storing event-user-item (EUI) information in an EUI database; and an analysis system for analyzing EUI information to provide item preferences and trend analysis.