Patents by Inventor Sujatha Pothireddy
Sujatha Pothireddy 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).
-
COMPUTERIZED ENGINES AND GRAPHICAL USER INTERFACES FOR CUSTOMIZING AND VALIDATING FORECASTING MODELS
Publication number: 20230297809Abstract: Some examples can involve a system that can receive a first user selection of time series data and a second user selection of a type of forecasting model to apply to the time series data. The system can then obtain a first set of candidate values and a second set of candidate values for a first parameter and a second parameter, respectively, of the selected type of forecasting model. The candidate values may be determined based on statistical information derived from the time series data. The system can then provide the first set of candidate values and the second set of candidate values to the user, receive user selections of a first parameter value and a second parameter value, and determine whether a conflict exists between the first parameter value and the second parameter value. If so, the system can generate an output indicating that the conflict exists.Type: ApplicationFiled: February 27, 2023Publication date: September 21, 2023Inventors: Iman Vasheghani Farahani, Ron Travis Hodgin, Sujatha Pothireddy, Kaushal Lalitkumar Chauhan, Bhupendra Suresh Bendale, Harshad Dinesh Bapat, Kritika Misra -
Computerized engines and graphical user interfaces for customizing and validating forecasting models
Patent number: 11748597Abstract: Some examples can involve a system that can receive a first user selection of time series data and a second user selection of a type of forecasting model to apply to the time series data. The system can then obtain a first set of candidate values and a second set of candidate values for a first parameter and a second parameter, respectively, of the selected type of forecasting model. The candidate values may be determined based on statistical information derived from the time series data. The system can then provide the first set of candidate values and the second set of candidate values to the user, receive user selections of a first parameter value and a second parameter value, and determine whether a conflict exists between the first parameter value and the second parameter value. If so, the system can generate an output indicating that the conflict exists.Type: GrantFiled: February 27, 2023Date of Patent: September 5, 2023Assignee: SAS Institute, Inc.Inventors: Iman Vasheghani Farahani, Ron Travis Hodgin, Sujatha Pothireddy, Kaushal Lalitkumar Chauhan, Bhupendra Suresh Bendale, Harshad Dinesh Bapat, Kritika Misra -
Patent number: 10560313Abstract: A pipeline system for time-series data forecasting using a distributed computing environment is disclosed herein. In one example, a pipeline for forecasting time series is generated. The pipeline represents a sequence of operations for processing the time series to produce forecasts. The sequence of operations include model strategy operations for applying various model strategies to the time series to determine error distributions corresponding to the model strategies. The sequence of operations further include a model-strategy comparison operation for determining which of the model strategies is a champion model strategy for the plurality of time series based on the error distributions of the model strategies. The pipeline is executed to determine the champion model strategy for the time series.Type: GrantFiled: June 26, 2019Date of Patent: February 11, 2020Assignee: SAS INSTITUTE INC.Inventors: Udo Vincenzo Sglavo, Phillip Mark Helmkamp, Jerzy Michal Brzezicki, Timothy Patrick Haley, Sujatha Pothireddy
-
Publication number: 20190394083Abstract: A pipeline system for time-series data forecasting using a distributed computing environment is disclosed herein. In one example, a pipeline for forecasting time series is generated. The pipeline represents a sequence of operations for processing the time series to produce forecasts. The sequence of operations include model strategy operations for applying various model strategies to the time series to determine error distributions corresponding to the model strategies. The sequence of operations further include a model-strategy comparison operation for determining which of the model strategies is a champion model strategy for the plurality of time series based on the error distributions of the model strategies. The pipeline is executed to determine the champion model strategy for the time series.Type: ApplicationFiled: June 26, 2019Publication date: December 26, 2019Applicant: SAS Institute Inc.Inventors: Udo Vincenzo Sglavo, Phillip Mark Helmkamp, Jerzy Michal Brzezicki, Timothy Patrick Haley, Sujatha Pothireddy
-
Patent number: 10037305Abstract: Systems and methods are provided for analyzing unstructured time stamped data. A distribution of time-stamped data is analyzed to identify a plurality of potential time series data hierarchies for structuring the data. An analysis of a potential time series data hierarchy may be performed. The analysis of the potential time series data hierarchies may include determining an optimal time series frequency and a data sufficiency metric for each of the potential time series data hierarchies. One of the potential time series data hierarchies may be selected based on a comparison of the data sufficiency metrics. Multiple time series may be derived in a single-read pass according to the selected time series data hierarchy. A time series forecast corresponding to at least one of the derived time series may be generated.Type: GrantFiled: February 6, 2018Date of Patent: July 31, 2018Assignee: SAS INSTITUTE INC.Inventors: Michael James Leonard, Edward Tilden Blair, Jerzy Michal Brzezicki, Udo V. Sglavo, Sujatha Pothireddy
-
Patent number: 10025753Abstract: Systems and methods are provided for analyzing unstructured time stamped data. A distribution of time-stamped data is analyzed to identify a plurality of potential time series data hierarchies for structuring the data. An analysis of a potential time series data hierarchy may be performed. The analysis of the potential time series data hierarchies may include determining an optimal time series frequency and a data sufficiency metric for each of the potential time series data hierarchies. One of the potential time series data hierarchies may be selected based on a comparison of the data sufficiency metrics. Multiple time series may be derived in a single-read pass according to the selected time series data hierarchy. A time series forecast corresponding to at least one of the derived time series may be generated.Type: GrantFiled: February 6, 2018Date of Patent: July 17, 2018Assignee: SAS INSTITUTE INC.Inventors: Michael James Leonard, Edward Tilden Blair, Jerzy Michal Brzezicki, Udo V. Sglavo, Sujatha Pothireddy
-
Publication number: 20180157620Abstract: Systems and methods are provided for analyzing unstructured time stamped data. A distribution of time-stamped data is analyzed to identify a plurality of potential time series data hierarchies for structuring the data. An analysis of a potential time series data hierarchy may be performed. The analysis of the potential time series data hierarchies may include determining an optimal time series frequency and a data sufficiency metric for each of the potential time series data hierarchies. One of the potential time series data hierarchies may be selected based on a comparison of the data sufficiency metrics. Multiple time series may be derived in a single-read pass according to the selected time series data hierarchy. A time series forecast corresponding to at least one of the derived time series may be generated.Type: ApplicationFiled: February 6, 2018Publication date: June 7, 2018Applicant: SAS Institute Inc.Inventors: Michael James Leonard, Edward Tilden Blair, Jerzy Michal Brzezicki, Udo V. Sglavo, Sujatha Pothireddy
-
Publication number: 20180157619Abstract: Systems and methods are provided for analyzing unstructured time stamped data. A distribution of time-stamped data is analyzed to identify a plurality of potential time series data hierarchies for structuring the data. An analysis of a potential time series data hierarchy may be performed. The analysis of the potential time series data hierarchies may include determining an optimal time series frequency and a data sufficiency metric for each of the potential time series data hierarchies. One of the potential time series data hierarchies may be selected based on a comparison of the data sufficiency metrics. Multiple time series may be derived in a single-read pass according to the selected time series data hierarchy. A time series forecast corresponding to at least one of the derived time series may be generated.Type: ApplicationFiled: February 6, 2018Publication date: June 7, 2018Applicant: SAS Institute Inc.Inventors: Michael James Leonard, Edward Tilden Blair, Jerzy Michal Brzezicki, Udo V. Sglavo, Sujatha Pothireddy
-
Patent number: 9916282Abstract: Systems and methods are provided for analyzing unstructured time stamped data. A distribution of time-stamped data is analyzed to identify a plurality of potential time series data hierarchies for structuring the data. An analysis of a potential time series data hierarchy may be performed. The analysis of the potential time series data hierarchies may include determining an optimal time series frequency and a data sufficiency metric for each of the potential time series data hierarchies. One of the potential time series data hierarchies may be selected based on a comparison of the data sufficiency metrics. Multiple time series may be derived in a single-read pass according to the selected time series data hierarchy. A time series forecast corresponding to at least one of the derived time series may be generated.Type: GrantFiled: June 10, 2015Date of Patent: March 13, 2018Assignee: SAS INSTITUTE INC.Inventors: Michael James Leonard, Edward Tilden Blair, Jerzy Michal Brzezicki, Udo V. Sglavo, Ranbir Singh Tomar, Kannukuzhiyil Kurien Kurien, Sujatha Pothireddy, Rajib Nath, Vilochan Suresh Muley
-
Publication number: 20150278153Abstract: Systems and methods are provided for analyzing unstructured time stamped data. A distribution of time-stamped data is analyzed to identify a plurality of potential time series data hierarchies for structuring the data. An analysis of a potential time series data hierarchy may be performed. The analysis of the potential time series data hierarchies may include determining an optimal time series frequency and a data sufficiency metric for each of the potential time series data hierarchies. One of the potential time series data hierarchies may be selected based on a comparison of the data sufficiency metrics. Multiple time series may be derived in a single-read pass according to the selected time series data hierarchy. A time series forecast corresponding to at least one of the derived time series may be generated.Type: ApplicationFiled: June 10, 2015Publication date: October 1, 2015Inventors: Michael James Leonard, Edward Tilden Blair, Jerzy Michal Brzezicki, Udo V. Sglavo, Ranbir Singh Tomar, Kannukuzhiyil Kurien Kurien, Sujatha Pothireddy, Rajib Nath, Vilochan Suresh Muley
-
Patent number: 9087306Abstract: Systems and methods are provided for analyzing unstructured time stamped data of a physical process in order to generate structured hierarchical data for a hierarchical time series analysis application. A plurality of time series analysis functions are selected from a functions repository. Distributions of time stamped unstructured data are analyzed to identify a plurality of potential hierarchical structures for the unstructured data with respect to the selected time series analysis functions.Type: GrantFiled: July 13, 2012Date of Patent: July 21, 2015Assignee: SAS Institute Inc.Inventors: Michael James Leonard, Edward Tilden Blair, Jerzy Michal Brzezicki, Udo V. Sglavo, Ranbir Singh Tomar, Kannukuzhiyil Kurien Kurien, Sujatha Pothireddy, Rajib Nath, Vilochan Suresh Muley
-
Publication number: 20140019088Abstract: Systems and methods are provided for analyzing unstructured time stamped data of a physical process in order to generate structured hierarchical data for a hierarchical time series analysis application. A plurality of time series analysis functions are selected from a functions repository. Distributions of time stamped unstructured data are analyzed to identify a plurality of potential hierarchical structures for the unstructured data with respect to the selected time series analysis functions.Type: ApplicationFiled: July 13, 2012Publication date: January 16, 2014Inventors: Michael James LEONARD, Edward Tilden BLAIR, Jerzy Michal BRZEZICKI, Udo V. SGLAVO, Ranbir Singh TOMAR, Kannukuzhiyil Kurien KURIEN, Sujatha POTHIREDDY, Rajib NATH, Vilochan Suresh MULEY
-
Patent number: 6314482Abstract: A method and system for indexing adapters within a data processing system where the data processing system contains multiple existing adapters, where each of the multiple existing adapters is identified by particular indexing data. All adapters within the data processing system are scanned. A determination of whether or not any additional adapters have been added to the data processing system in addition to the multiple existing adapters is made. Particular indexing data is assigned to any additional adapters in response to determining that additional adapters have been added to the data processing system, where any additional adapters added to the data processing system are indexed into the data processing system without changing the particular indexing data of each of the multiple existing adapters.Type: GrantFiled: March 19, 1999Date of Patent: November 6, 2001Assignee: International Business Machines CorporationInventors: Simon Chu, Richard Christopher Fore, Dean Alan Kalman, Robert Victor Miller, Sujatha Pothireddy, Robert Paul Rowe, Marty Eugene Turner
-
Patent number: 6266708Abstract: A framework for use with object-oriented programming systems includes one or more objects of a class called “Socket” that receive and process packets of work. As various applications execute, they require servicing of tasks, which correspond to the packets of work mentioned above. The packets of work are represented in the framework by objects of a class called “WorkUnit”. When a WorkUnit object is generated by an application, it in turn generates an object of a class called “Retriever” which is associated with the appropriate Socket object needed for servicing the WorkUnit. The Retriever object retrieves the Socket object to service the WorkUnit from an object of a class called “SessionInfo”. The SessionInfo object is a single object for maintaining registries of Socket objects and objects of a class called “ApplicationInfo”.Type: GrantFiled: July 21, 1995Date of Patent: July 24, 2001Assignee: International Business Machines CorporationInventors: Shawn M. Austvold, Rebecca B. Legler, Marshall P. Cline, Daniel R. Dahl, Jim Evans, Peter M. Gaertner, Neal Hale, Sujatha Pothireddy