Patents by Inventor Devavrat Shah
Devavrat Shah 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: 20230021223Abstract: Methods and systems for event prediction. The system includes at least one connector configured to gather at least partially incomplete data from at least one data source. The gathered data may be communicated to a model definition module that converts at least a subset of the gathered data into a prediction model in accordance with a received definition. A prediction module may receive a prediction query and, in response, supply an event prediction based on the prediction model.Type: ApplicationFiled: September 20, 2022Publication date: January 19, 2023Inventors: Ying-zong Huang, Vishal Doshi, Balaji Rengarajan, Vasudha Shivamoggi, Devavrat Shah, Ritesh Madan
-
Patent number: 11481644Abstract: A system includes at least one connector configured to gather at least partially incomplete data from at least one data source. The gathered data is communicated to a model definition module that converts at least a subset of the gathered data into a prediction model in accordance with a received definition. A prediction module receives a prediction query and, in response, supplies an event prediction based on the prediction model.Type: GrantFiled: December 17, 2017Date of Patent: October 25, 2022Assignee: NIKE, Inc.Inventors: Ying-zong Huang, Vishal Doshi, Balaji Rengarajan, Vasudha Shivamoggi, Devavrat Shah, Ritesh Madan
-
Patent number: 11062224Abstract: Methods and apparatus for predicting unknown values given a data set of known values. A prediction engine ingests a variety of data sets. Once the dataset has been ingested, requests for predictions may be presented to the prediction engine. The engine responds with a prediction as well as a confidence score based on the ingested information using a variety of techniques. Some of these techniques identify witness values in the ingested data that are similar to the requested prediction, other techniques compute witness values from ingested data, etc. These witness values are aggregated to yield an answer and a confidence level in a way that permits the user to review the underlying witness values.Type: GrantFiled: October 14, 2016Date of Patent: July 13, 2021Assignee: NIKE, Inc.Inventors: George Chen, Vishal Doshi, Ying-zong Huang, Vighnesh Sachidananda, Devavrat Shah, Vasudha Shivamoggi
-
Publication number: 20210109894Abstract: A computer-implemented method for automatically determining data relationships includes generating a graphical user interface (GUI) that allows a user to intuitively form a customized model of data from different data sources. The GUI includes icons that represent data sources, data variable selection, data modeling, and data prediction. The icons can be logically arranged to form a customized model without any additional user input or knowledge of data modeling. A prediction GUI allows the user to set customized weights of data variables in the model to form predictive controls for data prediction such as in what-if scenarios.Type: ApplicationFiled: October 13, 2020Publication date: April 15, 2021Inventors: Vinayak Ramesh, Devavrat Shah
-
Publication number: 20190303774Abstract: Systems and methods for completing at least one entry in a dataset. The systems and methods described herein find a rich set of dense features for each of a plurality of entities, then combine the rich set of dense features with externally provided features to estimate a target value. The systems and methods combine these features using a neural network model in which portions of the input layer are each only connected to a portion of the hidden layer.Type: ApplicationFiled: March 29, 2019Publication date: October 3, 2019Inventors: Devavrat Shah, Sai Kiran Burle, Ritesh Madan
-
Patent number: 10397747Abstract: Systems and methods for tracking at least one entity. Systems according to various embodiments may include an interface for at least receiving training data representing movements of a plurality of training entities and a query regarding a test entity's movement, a memory, and at least one processor executing instructions stored on the memory to create a plurality of tracks, generate an index of the plurality of tracks, execute the received query, and output a feature value with respect to the test entity.Type: GrantFiled: November 13, 2018Date of Patent: August 27, 2019Assignee: Celect, Inc.Inventors: Sai Kiran Burle, Joshua Lee, Devavrat Shah, Vishal Doshi, Ying-zong Huang, Quan Li
-
Publication number: 20190200167Abstract: Systems and methods for tracking at least one entity. Systems according to various embodiments may include an interface for at least receiving training data representing movements of a plurality of training entities and a query regarding a test entity's movement, a memory, and at least one processor executing instructions stored on the memory to create a plurality of tracks, generate an index of the plurality of tracks, execute the received query, and output a feature value with respect to the test entity.Type: ApplicationFiled: November 13, 2018Publication date: June 27, 2019Inventors: Sai Kiran Burle, Joshua Lee, Devavrat Shah, Vishal Doshi, Ying-zong Huang, Quan Li
-
Publication number: 20180240024Abstract: Methods and systems for event prediction. The system includes at least one connector configured to gather at least partially incomplete data from at least one data source. The gathered data may be communicated to a model definition module that converts at least a subset of the gathered data into a prediction model in accordance with a received definition. A prediction module may receive a prediction query and, in response, supply an event prediction based on the prediction model.Type: ApplicationFiled: December 17, 2017Publication date: August 23, 2018Inventors: Ying-zong Huang, Vishal Doshi, Balaji Rengarajan, Vasudha Shivamoggi, Devavrat Shah, Ritesh Madan
-
Publication number: 20180107763Abstract: Methods and apparatus for predicting unknown values given a data set of known values. A prediction engine ingests a variety of data sets. Once the dataset has been ingested, requests for predictions may be presented to the prediction engine. The engine responds with a prediction as well as a confidence score based on the ingested information using a variety of techniques. Some of these techniques identify witness values in the ingested data that are similar to the requested prediction, other techniques compute witness values from ingested data, etc. These witness values are aggregated to yield an answer and a confidence level in a way that permits the user to review the underlying witness values.Type: ApplicationFiled: October 14, 2016Publication date: April 19, 2018Inventors: George Chen, Vishal Doshi, Ying-zong Huang, Vighnesh Sachidananda, Devavrat Shah, Vasudha Shivamoggi
-
Patent number: 9251527Abstract: A system and method for providing a personalized recommendation from a series of partial preferences is presented. A preference distribution of a population including a plurality of weighted ranked lists is identified. A revealed preference of a user is compared to the plurality of ranked lists. An affinity weight between the user and each of the plurality of ranked lists is assigned, and a weighted average of each of the affinity weights is taken.Type: GrantFiled: August 29, 2012Date of Patent: February 2, 2016Assignee: Massachusetts Institute of TechnologyInventors: Devavrat Shah, Vivek Francis Farias, Srikanth Jagabathula, Ammar Tawfiq Ammar
-
Patent number: 9201968Abstract: A system and method for determining a rank aggregation from a series of partial preferences is presented. A distribution is learned over preferences from partial preferences with sparse support. A computer receives a plurality of partial preferences selected from two or more preference lists. Weights are assigned to each of said plurality of partial preferences, resulting in multiple ranked lists.Type: GrantFiled: August 29, 2012Date of Patent: December 1, 2015Assignee: Massachusetts Institute of TechnologyInventors: Devavrat Shah, Vivek Francis Farias, Srikanth Jagabathula, Ammar Tawfiq Ammar
-
Patent number: 9143175Abstract: In one aspect, a wireless system includes an encoder configured to encode data using a spinal code which uses a function over the message bits to directly produce a sequence of constellation symbols for transmission. The wireless system also includes a decoder configured to decode the spinal code. The function may be at least one of a non-linear function and a hash function.Type: GrantFiled: March 31, 2014Date of Patent: September 22, 2015Assignee: Massachusetts Institute of TechnologyInventors: Jonathan Perry, Devavrat Shah, Hari Balakrishnan
-
Publication number: 20140211881Abstract: In one aspect, a wireless system includes an encoder configured to encode data using a spinal code which uses a function over the message bits to directly produce a sequence of constellation symbols for transmission. The wireless system also includes a decoder configured to decode the spinal code. The function may be at least one of a non-linear function and a hash function.Type: ApplicationFiled: March 31, 2014Publication date: July 31, 2014Applicant: MASSACHUSETTS INSTITUTE OF TECHNOLOGYInventors: Jonathan Perry, Devavrat Shah, Hari Balakrishnan
-
Patent number: 8724715Abstract: In one aspect, a wireless system includes an encoder configured to encode data using a spinal code which uses a function over the message bits to directly produce a sequence of constellation symbols for transmission. The wireless system also includes a decoder configured to decode the spinal code. The function may be at least one of a non-linear function and a hash function.Type: GrantFiled: February 17, 2012Date of Patent: May 13, 2014Assignee: Massachusetts Institute of TechnologyInventors: Jonathan Perry, Devavrat Shah, Hari Balakrishnan
-
Patent number: 8526451Abstract: A method, apparatus and computer program product for providing network based flow control is presented. A linear combination of packets to transmit from a transmit queue is determined. The linear combination of packets is transmitted across a network using a sliding window protocol. An acknowledgement (ACK) is generated, wherein a packet is acknowledged when a receiving node receives the linear combination of packets and determines which packet of the linear combination of packets has been newly seen.Type: GrantFiled: February 24, 2012Date of Patent: September 3, 2013Assignees: President and Fellow of Harvard College, Universidade do Porto, Massachusetts Institute of TechnologyInventors: Jay Kumar Sundararajan, Devavrat Shah, Muriel Medard, Michael Mitzenmacher, Joao Barros, Szymon Jakubczak
-
Publication number: 20130054616Abstract: A system and method for determining a rank aggregation from a series of partial preferences is presented. A distribution is learned over preferences from partial preferences with sparse support. A computer receives a plurality of partial preferences selected from two or more preference lists. Weights are assigned to each of said plurality of partial preferences, resulting in multiple ranked lists.Type: ApplicationFiled: August 29, 2012Publication date: February 28, 2013Applicant: MASSACHUSETTS INSTITUTE OF TECHNOLOGYInventors: Ammar Tawfiq Ammar, Vivek Francis Farias, Srikanth Jagabathula, Devavrat Shah
-
Publication number: 20130054498Abstract: A system and method for providing a personalized recommendation from a series of partial preferences is presented. A preference distribution of a population including a plurality of weighted ranked lists is identified. A revealed preference of a user is compared to the plurality of ranked lists. An affinity weight between the user and each of the plurality of ranked lists is assigned, and a weighted average of each of the affinity weights is taken.Type: ApplicationFiled: August 29, 2012Publication date: February 28, 2013Applicant: MASSACHUSETTS INSTITUTE OF TECHNOLOGYInventors: Devavrat Shah, Vivek Francis Farias, Srikanth Jagabathula, Ammar Tawfiq Ammar
-
Publication number: 20120218891Abstract: A method, apparatus and computer program product for providing network based flow control is presented. A linear combination of packets to transmit from a transmit queue is determined. The linear combination of packets is transmitted across a network using a sliding window protocol. An acknowledgement (ACK) is generated, wherein a packet is acknowledged when a receiving node receives the linear combination of packets and determines which packet of the linear combination of packets has been newly seen.Type: ApplicationFiled: February 24, 2012Publication date: August 30, 2012Inventors: Jay Kumar Sundararajan, Devavrat Shah, Muriel Medard, Michael Mitzenmacher, Joao Barros, Szymon Jakubczak
-
Publication number: 20120213307Abstract: In one aspect, a wireless system includes an encoder configured to encode data using a spinal code which uses a function over the message bits to directly produce a sequence of constellation symbols for transmission. The wireless system also includes a decoder configured to decode the spinal code. The function may be at least one of a non-linear function and a hash function.Type: ApplicationFiled: February 17, 2012Publication date: August 23, 2012Applicant: Massachusetts Institute of TechnologyInventors: Jonathan Perry, Devavrat Shah, Hari Balakrishnan
-
Patent number: 8130776Abstract: A method, apparatus and computer program product for providing network based flow control is presented. A linear combination of packets to transmit from a transmit queue is determined. The linear combination of packets is transmitted across a network using a sliding window protocol. An acknowledgement (ACK) is generated, wherein a packet is acknowledged when a receiving node receives the linear combination of packets and determines which packet of the linear combination of packets has been newly seen.Type: GrantFiled: August 28, 2009Date of Patent: March 6, 2012Assignee: Massachusetts Institute of TechnologyInventors: Jay Kumar Sundararajan, Devavrat Shah, Muriel Medard, Michael Mitzenmacher, Joao Barros, Szymon Jakubczak