Patents by Inventor Prashant Gaurav
Prashant Gaurav 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: 20230214696Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for presenting a recommendation. In one embodiment, a system is introduced that includes a plurality of models for obtaining a recommendation score. The recommendation score may be obtained using one or more models which can include supervised and unsupervised learning as well as a combination of user information and transactions. In another embodiment, the system is introduced that can provide a total recommendation score and recommendation generated by an ensemble model whose input can include the one or more recommendation scores previously obtained.Type: ApplicationFiled: December 16, 2022Publication date: July 6, 2023Inventors: Dinesh Kumar, Yuanyuan Pan, Prashant Gaurav, Fransisco Kurniadi, Kevin Ward, Yue Xin, Krishnakumar Govindarajalu, Kimberly Kidney, Tao Sun
-
Patent number: 11676162Abstract: A method, apparatus, and computer program product are disclosed for improved machine learning using a statistical model. In the context of an apparatus, some example embodiments include a processor configured to cause retrieval of information regarding a plurality of consumers, and modeling circuitry configured to train a statistical model of the plurality of consumers based on the retrieved information, and predict, using the statistical model, an incremental booking value associated with the promotion for each consumer of the plurality of consumers. The processor is further configured to select a subset of the plurality of consumers for receiving impressions of the promotion. Some example embodiments may further include communications circuitry configured to transmit an impression of the promotion to each consumer in the subset of the plurality of consumers.Type: GrantFiled: March 29, 2021Date of Patent: June 13, 2023Assignee: Groupon, Inc.Inventors: Rajesh Girish Parekh, Raju Balakrishnan, Guoxian Zhang, Prashant Gaurav
-
Patent number: 11531916Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for presenting a recommendation. In one embodiment, a system is introduced that includes a plurality of models for obtaining a recommendation score. The recommendation score may be obtained using one or more models which can include supervised and unsupervised learning as well as a combination of user information and transactions. In another embodiment, the system is introduced that can provide a total recommendation score and recommendation generated by an ensemble model whose input can include the one or more recommendation scores previously obtained.Type: GrantFiled: December 7, 2018Date of Patent: December 20, 2022Assignee: PayPal, Inc.Inventors: Dinesh Kumar, Yuanyuan Pan, Prashant Gaurav, Fransisco Kurniadi, Kevin Ward, Yue Xin, Krishnakumar Govindarajalu, Kimberly Kidney, Tao Sun
-
Publication number: 20220292526Abstract: A method, apparatus, and computer program product are disclosed for improved promotion targeting. An example apparatus includes a processor configured to cause retrieval of historical information regarding transactions associated with a plurality of identifier entities. The example apparatus further includes modeling circuitry configured to train a statistical model using the retrieved historical information, and estimate, using the statistical model, values for expected identifier entity transaction requests associated with each of the plurality of identifier entities. The processor of the example apparatus may further be configured to select, based on the estimated values, a subset of identifier entities to receive impressions of the promotion, and the apparatus may further include communications circuitry configured to transmit an impression of the promotion to each identifier entity in the subset.Type: ApplicationFiled: March 30, 2022Publication date: September 15, 2022Inventors: Rajesh Girish PAREKH, Raju BALAKRISHNAN, Guoxian ZHANG, Prashant GAURAV
-
Patent number: 11308506Abstract: A method, apparatus, and computer program product are disclosed for improved promotion targeting. An example apparatus includes a processor configured to cause retrieval of historical information regarding transactions associated with a plurality of identifier entities. The example apparatus further includes modeling circuitry configured to train a statistical model using the retrieved historical information, and estimate, using the statistical model, values for expected identifier entity transaction requests associated with each of the plurality of identifier entities. The processor of the example apparatus may further be configured to select, based on the estimated values, a subset of identifier entities to receive impressions of the promotion, and the apparatus may further include communications circuitry configured to transmit an impression of the promotion to each identifier entity in the subset.Type: GrantFiled: August 4, 2020Date of Patent: April 19, 2022Assignee: Groupon, Inc.Inventors: Rajesh Girish Parekh, Raju Balakrishnan, Guoxian Zhang, Prashant Gaurav
-
Publication number: 20210374799Abstract: Various methods are provided for intelligently modeling a diverse promotion portfolio. One example method may comprise utilizing an analytical model to intelligently generate a proposed promotion portfolio of available promotions by performing an iterative process in which a determination is made as to whether the proposed promotion portfolio that is generated projects a predicted revenue that at least meets the target revenue over the predefined period of time for the geographic area, in an instance in which the determined proposed promotion portfolio value fails to meet the target revenue over the predefined period of time for the geographic area, repeating the iterative process and altering the weighting values, in an instance in which the determined proposed promotion portfolio value at least meets the target revenue over the predefined period of time for the geographic area, ending iterative process, and generating the inventory of promotions in accordance with the proposed promotion portfolio.Type: ApplicationFiled: February 22, 2021Publication date: December 2, 2021Inventors: Prashant GAURAV, Rajesh PAREKH, Michalis POTAMIAS
-
Patent number: 11157987Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for presenting a recommendation. In one embodiment, a system is introduced that includes a plurality of models for obtaining a recommendation score. The recommendation score may be obtained using one or more recommendation models and a recommendation made based on the recommendation score determined. In another embodiment, the system is introduced that can re-train the recommendation model based on a feedback received in response to a recommendation made using on the recommendation score obtained.Type: GrantFiled: December 11, 2018Date of Patent: October 26, 2021Assignee: PayPal, Inc.Inventors: Dinesh Kumar, Yuanyuan Pan, Prashant Gaurav, Fransisco Kurniadi, Yue Xin, Krishnakumar Govindarajalu, Kimberly Kidney, Tao Sun, Kevin Ward
-
Publication number: 20210319459Abstract: A method, apparatus, and computer program product are disclosed for improved machine learning using a statistical model. In the context of an apparatus, some example embodiments include a processor configured to cause retrieval of information regarding a plurality of consumers, and modeling circuitry configured to train a statistical model of the plurality of consumers based on the retrieved information, and predict, using the statistical model, an incremental booking value associated with the promotion for each consumer of the plurality of consumers. The processor is further configured to select a subset of the plurality of consumers for receiving impressions of the promotion. Some example embodiments may further include communications circuitry configured to transmit an impression of the promotion to each consumer in the subset of the plurality of consumers.Type: ApplicationFiled: March 29, 2021Publication date: October 14, 2021Inventors: Rajesh Girish PAREKH, Raju BALAKRISHNAN, Guoxian ZHANG, Prashant GAURAV
-
Publication number: 20210240828Abstract: An amount of data change associated with a version of a content file with respect to one or more previous versions of the content file is determined. The amount of change associated with the version of the content file is determined using a tree data structure associated with the content file that is stored on a storage cluster. One or more statistics associated with backup snapshot are provided to a server. The server is configured to determine that the amount of data change associated with the version of the content file is anomalous based in part on the one or more statistics associated with the backup snapshot. A notification that data associated with the backup snapshot is potentially infected by malicious software is received from the server. The version of the content file is indicated as being potentially infected by malicious software.Type: ApplicationFiled: January 22, 2021Publication date: August 5, 2021Inventors: Prashant Gaurav, Sidharth Mishra, Karandeep Singh Chawla, Anubhav Gupta, Sudhir Srinivas, Apurv Gupta, Nagapramod Mandagere
-
Patent number: 10990987Abstract: A method, apparatus, and computer program product are disclosed for improved machine learning using a statistical model. In the context of an apparatus, some example embodiments include a processor configured to cause retrieval of information regarding a plurality of consumers, and modeling circuitry configured to train a statistical model of the plurality of consumers based on the retrieved information, and predict, using the statistical model, an incremental booking value associated with the promotion for each consumer of the plurality of consumers. The processor is further configured to select a subset of the plurality of consumers for receiving impressions of the promotion. Some example embodiments may further include communications circuitry configured to transmit an impression of the promotion to each consumer in the subset of the plurality of consumers.Type: GrantFiled: August 27, 2019Date of Patent: April 27, 2021Assignee: Groupon, Inc.Inventors: Rajesh Girish Parekh, Raju Balakrishnan, Guoxian Zhang, Prashant Gaurav
-
Patent number: 10951600Abstract: Various systems and methods for domain authentication are described herein. In an example, the method may include detecting a domain from a request of a tenant for access to a farm. The method may also include identifying a presence of a site ID from a database of the farm based on the domain. The method may also include sending an authentication request to a default site or a custom site, the authentication request managed through a site manager based on the identified presence of the site ID in the database of the farm. The method may also include routing traffic from the tenant to the farm in response to satisfaction of the authentication request.Type: GrantFiled: May 8, 2017Date of Patent: March 16, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Kalyan K. Kona, Patrick J. Simek, Le Chang, Roshane Silva, Prashant Gaurav
-
Patent number: 10943011Abstract: An amount of data change associated with a version of a content file with respect to one or more previous versions of the content file is determined. The amount of change associated with the version of the content file is determined using a tree data structure associated with the content file that is stored on a storage cluster. One or more statistics associated with backup snapshot are provided to a server. The server is configured to determine that the amount of data change associated with the version of the content file is anomalous based in part on the one or more statistics associated with the backup snapshot. A notification that data associated with the backup snapshot is potentially infected by malicious software is received from the server. The version of the content file is indicated as being potentially infected by malicious software.Type: GrantFiled: March 27, 2020Date of Patent: March 9, 2021Assignee: Cohesity, Inc.Inventors: Prashant Gaurav, Sidharth Mishra, Karandeep Singh Chawla, Anubhav Gupta, Sudhir Srinivas, Apurv Gupta, Nagapramod Mandagere
-
Publication number: 20210019771Abstract: A method, apparatus, and computer program product are disclosed for improved promotion targeting. An example apparatus includes a processor configured to cause retrieval of historical information regarding transactions associated with a plurality of identifier entities. The example apparatus further includes modeling circuitry configured to train a statistical model using the retrieved historical information, and estimate, using the statistical model, values for expected identifier entity transaction requests associated with each of the plurality of identifier entities. The processor of the example apparatus may further be configured to select, based on the estimated values, a subset of identifier entities to receive impressions of the promotion, and the apparatus may further include communications circuitry configured to transmit an impression of the promotion to each identifier entity in the subset.Type: ApplicationFiled: August 4, 2020Publication date: January 21, 2021Inventors: Rajesh Girish Parekh, Raju BALAKRISHNAN, Guoxian ZHANG, Prashant GAURAV
-
Patent number: 10783537Abstract: A method, apparatus, and computer program product are disclosed for improved promotion targeting. An example apparatus includes a processor configured to cause retrieval of historical information regarding transactions associated with a plurality of identifier entities. The example apparatus further includes modeling circuitry configured to train a statistical model using the retrieved historical information, and estimate, using the statistical model, values for expected identifier entity transaction requests associated with each of the plurality of identifier entities. The processor of the example apparatus may further be configured to select, based on the estimated values, a subset of identifier entities to receive impressions of the promotion, and the apparatus may further include communications circuitry configured to transmit an impression of the promotion to each identifier entity in the subset.Type: GrantFiled: March 29, 2016Date of Patent: September 22, 2020Assignee: Groupon, Inc.Inventors: Rajesh Girish Parekh, Raju Balakrishnan, Guoxian Zhang, Prashant Gaurav
-
Publication number: 20200226256Abstract: An amount of data change associated with a version of a content file with respect to one or more previous versions of the content file is determined. The amount of change associated with the version of the content file is determined using a tree data structure associated with the content file that is stored on a storage cluster. One or more statistics associated with backup snapshot are provided to a server. The server is configured to determine that the amount of data change associated with the version of the content file is anomalous based in part on the one or more statistics associated with the backup snapshot. A notification that data associated with the backup snapshot is potentially infected by malicious software is received from the server. The version of the content file is indicated as being potentially infected by malicious software.Type: ApplicationFiled: March 27, 2020Publication date: July 16, 2020Inventors: Prashant Gaurav, Sidharth Mishra, Karandeep Singh Chawla, Anubhav Gupta, Sudhir Srinivas, Apurv Gupta, Nagapramod Mandagere
-
Patent number: 10715494Abstract: Aspects of the present disclosure provide systems and methods for directly transferring tenant data hosted on a source domain to a target domain, wherein the source and target domains are associated with different server farms. Additionally, where the source domain is managed by a source management layer and the target domain is managed by target management layer, which source and target management layers are not in a trust relationship. Aspects describe establishing a secure, direct communication bus between the source and target management layers in order to accomplish a plurality of steps involved in transferring the tenant, wherein tenant data transferred thereon is encrypted. In example aspects, the direct communication bus terminates upon completion of the tenant data transfer.Type: GrantFiled: May 15, 2017Date of Patent: July 14, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Patrick J. Simek, Prashant Gaurav, Kalyan K. Kona, Ilker Celikyilmaz
-
Publication number: 20200219042Abstract: The present disclosure relates to methods, systems, and apparatuses for identifying related records in a database.Type: ApplicationFiled: January 2, 2020Publication date: July 9, 2020Inventors: Prashant Gaurav, Nipun Agarwal, Sushant Wason
-
Publication number: 20200184357Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for presenting a recommendation. In one embodiment, a system is introduced that includes a plurality of models for obtaining a recommendation score. The recommendation score may be obtained using one or more models which can include supervised and unsupervised learning as well as a combination of user information and transactions. In another embodiment, the system is introduced that can provide a total recommendation score and recommendation generated by an ensemble model whose input can include the one or more recommendation scores previously obtained.Type: ApplicationFiled: December 7, 2018Publication date: June 11, 2020Inventors: Dinesh Kumar, Yuanyuan Pan, Prashant Gaurav, Fransisco Kurniadi, Kevin Ward, Yue Xin, Krishnakumar Govindarajalu, Kimberly Kidney, Tao Sun
-
Publication number: 20200184537Abstract: Aspects of the present disclosure involve systems, methods, devices, and the like for presenting a recommendation. In one embodiment, a system is introduced that includes a plurality of models for obtaining a recommendation score. The recommendation score may be obtained using one or more recommendation models and a recommendation made based on the recommendation score determined. In another embodiment, the system is introduced that can re-train the recommendation model based on a feedback received in response to a recommendation made using on the recommendation score obtained.Type: ApplicationFiled: December 11, 2018Publication date: June 11, 2020Inventors: Dinesh Kumar, Yuanyuan Pan, Prashant Gaurav, Fransisco Kurniadi, Yue Xin, Krishnakumar Govindarajalu, Kimberly Kidney, Tao Sun, Kevin Ward
-
Patent number: 10650146Abstract: An amount of data change associated with a version of a content file with respect to one or more previous versions of the content file is determined. The amount of change associated with the version of the content file is determined using a tree data structure associated with the content file that is stored on a storage cluster. One or more statistics associated with backup snapshot are provided to a server. The server is configured to determine that the amount of data change associated with the version of the content file is anomalous based in part on the one or more statistics associated with the backup snapshot. A notification that data associated with the backup snapshot is potentially infected by malicious software is received from the server. The version of the content file is indicated as being potentially infected by malicious software.Type: GrantFiled: April 1, 2019Date of Patent: May 12, 2020Assignee: Cohesity, Inc.Inventors: Prashant Gaurav, Sidharth Mishra, Karandeep Singh Chawla, Anubhav Gupta, Sudhir Srinivas, Nagapramod Mandagere, Apurv Gupta