Patents by Inventor Amit Dhurandhar

Amit Dhurandhar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20180300790
    Abstract: Techniques facilitating interpretable rule generation using loss-preserving transformation are provided. In one example, a computer-implemented method can comprise evaluating, by a system operatively coupled to a processor, an input data set that comprises three data categories. The computer-implemented method can also comprise transforming, by the system, the input data set into a transformed data set. The transformed data set can comprise two data categories determined based on the three data categories. Transforming the input data set can comprise determining a first cost associated with the transformed data set is no greater than a second cost associated with the input data set.
    Type: Application
    Filed: April 17, 2017
    Publication date: October 18, 2018
    Inventors: Amit Dhurandhar, Sechan Oh, Marek Petrik
  • Publication number: 20180300792
    Abstract: Techniques facilitating interpretable rule generation using loss-preserving transformation are provided. In one example, a computer-implemented method can comprise evaluating, by a system operatively coupled to a processor, an input data set that comprises three data categories. The computer-implemented method can also comprise transforming, by the system, the input data set into a transformed data set. The transformed data set can comprise two data categories determined based on the three data categories. Transforming the input data set can comprise determining a first cost associated with the transformed data set is no greater than a second cost associated with the input data set.
    Type: Application
    Filed: December 14, 2017
    Publication date: October 18, 2018
    Inventors: Amit Dhurandhar, Sechan Oh, Marek Petrik
  • Publication number: 20180293683
    Abstract: A network is crawled using a trained learning model to identify a set of secondary-source documents related to an event. A hub page from the set of secondary-source documents is identified that includes a link predicted to link to a new relevant secondary-source document. The new document is added to the set of secondary-source documents. Information is extracted from the set of secondary-source documents. Feedback is received indicative of a relevancy level for the extracted information as applied to the event. Each document is classified into one or more categories related to the event, based on the extracted information and the received feedback information. A learning model is trained based on the received feedback.
    Type: Application
    Filed: April 11, 2017
    Publication date: October 11, 2018
    Inventors: Ioana M. Baldini Soares, Amit Dhurandhar, Abhishek Kumar, Aleksandra Mojsilovic, Kien T. Pham, Kush R. Varshney, Maja Vukovic
  • Publication number: 20180107803
    Abstract: Predicting human olfactory perception based on molecular structure is described. Molecular descriptor data indicative of molecular descriptors associated with a group of molecular samples can be obtained. Olfactory perception indicator (OPI) data for a set of OPIs can also be obtained with respect to the molecular samples. A training model can be executed on the molecular descriptor data and the OPI data to yield an output model that correlates molecular attributes with OPIs for a single individual or across an aggregate of individuals. The output model can be used to predict olfactory perception for a particular compound or mixture based on which OPIs are correlated with molecular descriptors of the compound or mixture in the output model. The output model can also be inverted and used to identify molecular descriptors that are correlated with a desired set of OPIs. A molecular construct having the molecular descriptors can then be generated.
    Type: Application
    Filed: October 18, 2016
    Publication date: April 19, 2018
    Inventors: Guillermo A. Cecchi, Amit Dhurandhar, Pablo Meyer rojas
  • Publication number: 20180089739
    Abstract: Systems, methods, and computer-readable media are described for predicting consumer response to a stimulus based on olfactory characteristics of the stimulus. An intrinsic factor score associated with a product can be determined based on an intrinsic attribute of the stimulus, and optionally, further based on data indicative of historical consumer response to olfactory characteristics of the stimulus. A social factor score associated with a user can also be determined using available olfactory preference data associated with the user and/or data representative of one or more social signals indicative of a predicted response of the user to olfactory characteristics of the stimulus. A collaborative filtering technique can be employed to determine a recommendation score for the stimulus using the intrinsic factor score and the social factor score. The recommendation score can be compared to a threshold value to determine whether to recommend the stimulus to the user.
    Type: Application
    Filed: September 28, 2016
    Publication date: March 29, 2018
    Inventors: Guillermo Cecchi, Amit Dhurandhar, Stacey M. Gifford, Raquel Norel, Pablo Meyer Rojas, Kahn Rhrissorrakrai, Bo Zhang
  • Patent number: 9915942
    Abstract: A method, a computer program product, and a computer system for identifying significant and consumable-insensitive trace features. A computer computes a residual in a first regression of one or more secondary factors on a target. The computer computes residuals in a second regression of the one or more secondary factors on each of one or more trace features in one or more trace feature sets. The computer computes, for the one or more trace feature sets, coefficients of determination in a third regression of the residuals in the second regression on the residual in the first regression. The computer ranks the one or more trace feature sets by sorting the coefficient of determination. The computer determines, based on rankings of the one or more trace feature sets, significant trace feature sets.
    Type: Grant
    Filed: March 20, 2015
    Date of Patent: March 13, 2018
    Assignee: International Business Machines Corporation
    Inventors: Robert J. Baseman, Amit Dhurandhar, Fateh A. Tipu
  • Publication number: 20170293917
    Abstract: An apparatus, method and computer program product for identifying fraud in transaction data. The method includes: receiving invoice data comprising a vendor, a requestor and events, receiving public data and private data sources, computing a vendor risk score using the public and private data sources matching the vendor of the invoice data, computing a requestor risk score using the public data sources and the private data sources matching the requestor of the invoice data, computing an active invoice score using the vendor risk score and the requestor risk score and when the active invoice score is greater than a predetermined amount, blocking the invoice data. In one embodiment, computing a vendor risk score comprises obtaining a weight and a confidence for the event, calculating an event vendor risk score using the weight times the confidence and combining the event vendor risk scores for all of the events.
    Type: Application
    Filed: April 8, 2016
    Publication date: October 12, 2017
    Inventors: Amit Dhurandhar, Markus Ettl, Bruce C. Graves, Gopikrishna Maniachari, Anthony T. Mazzatti, Rajesh Kumar Ravi
  • Patent number: 9600773
    Abstract: A method for detecting anomalous energy usage of building or household entities. The method applies a number of successively stringent anomaly detection techniques to isolate households that are highly suspect for having engaged in electricity theft via meter tampering. The system utilizes historical time series data of electricity usage, weather, and household characteristics (e.g., size, age, value) and provides a list of households that are worthy of a formal theft investigation. Generally, raw utility usage data, weather history data, and household characteristics are cleansed, and loaded into an analytics data mart. The data mart feeds four classes of anomaly detection algorithms developed, with each analytic producing a set of households suspected of having engaged in electricity theft. The system allows a user to select households from each list or a set based on the intersection of all individual sets.
    Type: Grant
    Filed: September 13, 2013
    Date of Patent: March 21, 2017
    Assignee: International Business Machines Corporation
    Inventors: Amit Dhurandhar, Jayant R. Kalagnanam, Stuart A. Siegel, Yada Zhu
  • Patent number: 9595006
    Abstract: A system and method for detecting anomalous energy usage of building or household entities. The method applies a number of successively stringent anomaly detection techniques to isolate households that are highly suspect for having engaged in electricity theft via meter tampering. The system utilizes historical time series data of electricity usage, weather, and household characteristics (e.g., size, age, value) and provides a list of households that are worthy of a formal theft investigation. Generally, raw utility usage data, weather history data, and household characteristics are cleansed, and loaded into an analytics data mart. The data mart feeds four classes of anomaly detection algorithms developed, with each analytic producing a set of households suspected of having engaged in electricity theft. The system allows a user to select households from each list or a set based on the intersection of all individual sets.
    Type: Grant
    Filed: June 4, 2013
    Date of Patent: March 14, 2017
    Assignee: International Business Machines Corporation
    Inventors: Amit Dhurandhar, Jayant R. Kalagnanam, Stuart A. Siegel, Yada Zhu
  • Publication number: 20160274177
    Abstract: A method, a computer program product, and a computer system for identifying significant and consumable-insensitive trace features. A computer computes a residual in a first regression of one or more secondary factors on a target. The computer computes residuals in a second regression of the one or more secondary factors on each of one or more trace features in one or more trace feature sets. The computer computes, for the one or more trace feature sets, coefficients of determination in a third regression of the residuals in the second regression on the residual in the first regression. The computer ranks the one or more trace feature sets by sorting the coefficient of determination. The computer determines, based on rankings of the one or more trace feature sets, significant trace feature sets.
    Type: Application
    Filed: March 20, 2015
    Publication date: September 22, 2016
    Inventors: Robert J. Baseman, Amit Dhurandhar, Fateh A. Tipu
  • Publication number: 20160203417
    Abstract: A system and method for extending partially labeled data graphs to unlabeled nodes in a single network classification by weighting the data with a weight matrix that uses a modified graph Laplacian based regularization framework and applying graph transduction methods to the weighted data. The technique may be applied to data graphs that are directed or undirected, that may or may not have attributes and that may be homogeneous or heterogeneous.
    Type: Application
    Filed: March 23, 2016
    Publication date: July 14, 2016
    Inventors: Amit Dhurandhar, Jun Wang
  • Patent number: 9355367
    Abstract: A system and method for extending partially labeled data graphs to unlabeled nodes in a single network classification by weighting the data with a weight matrix that uses a modified graph Laplacian based regularization framework and applying graph transduction methods to the weighted data. The technique may be applied to data graphs that are directed or undirected, that may or may not have attributes and that may be homogeneous or heterogeneous.
    Type: Grant
    Filed: March 7, 2013
    Date of Patent: May 31, 2016
    Assignee: International Business Machines Corporation
    Inventors: Amit Dhurandhar, Jun Wang
  • Publication number: 20150242856
    Abstract: A computer-based system provides identification and determination of possible fraud/risk in procurement. Both transactional data and social media data are analyzed to identify fraud and discover potentially colluding parties. A comprehensive solution incorporates text analytics, business/procurement rules, and social network analysis. Furthermore, both unsupervised and supervised machine learning can provide improved accuracy over time as more data is captured and analyzed and updates repeated. The system can include modular or integrated components, allowing for certain customized or commercially available components to be utilized in accordance with the comprehensive solution.
    Type: Application
    Filed: February 21, 2014
    Publication date: August 27, 2015
    Applicant: International Business Machines Corporation
    Inventors: Amit Dhurandhar, Markus R. Ettl, Bruce C. Graves, Rajesh K. Ravi
  • Publication number: 20140358838
    Abstract: A system and method for detecting anomalous energy usage of building or household entities. The method applies a number of successively stringent anomaly detection techniques to isolate households that are highly suspect for having engaged in electricity theft via meter tampering. The system utilizes historical time series data of electricity usage, weather, and household characteristics (e.g., size, age, value) and provides a list of households that are worthy of a formal theft investigation. Generally, raw utility usage data, weather history data, and household characteristics are cleansed, and loaded into an analytics data mart. The data mart feeds four classes of anomaly detection algorithms developed, with each analytic producing a set of households suspected of having engaged in electricity theft. The system allows a user to select households from each list or a set based on the intersection of all individual sets.
    Type: Application
    Filed: June 4, 2013
    Publication date: December 4, 2014
    Inventors: Amit Dhurandhar, Jayant R. Kalagnanam, Stuart A. Siegel, Yada Zhu
  • Publication number: 20140358839
    Abstract: A method for detecting anomalous energy usage of building or household entities. The method applies a number of successively stringent anomaly detection techniques to isolate households that are highly suspect for having engaged in electricity theft via meter tampering. The system utilizes historical time series data of electricity usage, weather, and household characteristics (e.g., size, age, value) and provides a list of households that are worthy of a formal theft investigation. Generally, raw utility usage data, weather history data, and household characteristics are cleansed, and loaded into an analytics data mart. The data mart feeds four classes of anomaly detection algorithms developed, with each analytic producing a set of households suspected of having engaged in electricity theft. The system allows a user to select households from each list or a set based on the intersection of all individual sets.
    Type: Application
    Filed: September 13, 2013
    Publication date: December 4, 2014
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Amit Dhurandhar, Jayant R. Kalagnanam, Stuart A. Siegel, Yada Zhu
  • Patent number: 8874409
    Abstract: A system, method and computer program product for improving a manufacturing or production environment. The system receives two or more time series data having values that represent current conditions of the manufacturing or production environment as inputs. The system determines one or more different regimes in the received two or more time series data. The system predicts future or unmeasured values of the received two or more time series data in the determined different regimes. The future or unmeasured values represent future conditions of the manufacturing or production environment.
    Type: Grant
    Filed: December 13, 2010
    Date of Patent: October 28, 2014
    Assignee: International Business Machines Corporation
    Inventors: Amit Dhurandhar, Jayant R. Kalagnanam
  • Publication number: 20140258196
    Abstract: A system and method for extending partially labeled data graphs to unlabeled nodes in a single network classification by weighting the data with a weight matrix that uses a modified graph Laplacian based regularization framework and applying graph transduction methods to the weighted data. The technique may be applied to data graphs that are directed or undirected, that may or may not have attributes and that may be homogeneous or heterogeneous.
    Type: Application
    Filed: March 7, 2013
    Publication date: September 11, 2014
    Applicant: International Business Machines Corporation
    Inventors: Amit Dhurandhar, Jun Wang
  • Patent number: 8793106
    Abstract: A system, method and computer program product for predicting at least one feature of at least one product being manufactured. The system receives, from at least one sensor installed in equipment performing one or more manufacturing process steps, at least one measurement of the feature of the product being manufactured. The system selects one or more of the received measurement of the feature of the product. The system estimates additional measurements of the feature of the product at a current manufacturing process step. The system creates a computational model for predicting future measurements of the feature of the product, based on the selected measurement and the estimated additional measurements. The system predicts the future measurements of the feature of the product based on the created computational model. The system outputs the predicted future measurements of the feature of the product.
    Type: Grant
    Filed: September 23, 2011
    Date of Patent: July 29, 2014
    Assignee: International Business Machines Corporation
    Inventors: Robert J. Baseman, Amit Dhurandhar, Sholom M. Weiss, Brian F. White
  • Patent number: 8762314
    Abstract: Predictions of a given predictive model may be improved using aggregate information. A plurality of targets to predict in a given domain may be identified, and may be predicted based on raw data set. Aggregate information associated with the plurality of targets is received, the aggregate information including estimated or actual values at a coarser level of the plurality of targets, and based on the aggregate information, the predicted target values may be improved in prediction accuracy.
    Type: Grant
    Filed: July 15, 2011
    Date of Patent: June 24, 2014
    Assignee: International Business Machines Corporation
    Inventor: Amit Dhurandhar
  • Patent number: 8732090
    Abstract: Managing spend compliance may include receiving a set of spend transaction records containing one or more spend attributes, one or more compliance business rules and one or more investment scenarios that increase spend compliance. The compliance business rules may be applied to the transaction records and segments of transactions with predetermined high savings opportunities may be determined. A prioritized investment plan over one or more time periods that yield optimized return on investment may be generated based on applying the segments of transactions and the investment scenarios.
    Type: Grant
    Filed: December 29, 2011
    Date of Patent: May 20, 2014
    Assignee: International Business Machines Corporation
    Inventors: Pawan R. Chowdhary, Amit Dhurandhar, Markus R. Ettl, Soumyadip Ghosh, Bruce C. Graves, William S. Schaefer, Karthik Sourirajan, Yu Tang