Search

Karan Singh Rekhi

from Sammamish, WA
Age ~39
Get Report
Also known as:
Karan S Rekhi, Karan Rehki, Karan Singh, Karan Rekhi Singh, Rekhi S Karan
Related to:
Jyotika Singh, 47
Connected to:
Inderpreet S Rekhi, 42Jaspreet K Rekhi, 53Navneeta Rekhi, 40Edward Rekhtman, 62Mark B Rekhtman, 78Amir Rekic, 51Indira Rekic, 56Lindsey L Rekieta, 41Ahmed Rekik, 45Curtis D Rekkedal, 75

Karan Rekhi Phones & Addresses

  • Sammamish, WA
  • Puyallup, WA
  • Kenmore, WA
    • s
  • 1227 NE Hickory Ln, Issaquah, WA 98029
  • Bellevue, WA
  • Seattle, WA
  • Stony Brook, NY

Resumes

Resumes

Karan Rekhi Photo 1

Principal Program Manager

View page
Location:
24240 southeast 10Th Pl, Sammamish, WA 98075
Industry:
Computer Software
Work:
Amazon
Senior Product Manager
Amazon Jul 2010 - Jun 2012
Software Development Engineer
Stony Brook Medicine Jun 2009 - Feb 2010
Senior Research Aide
National Instruments Jul 2007 - Jan 2009
Software Development Engineer
Microsoft Jul 2007 - Jan 2009
Principal Program Manager
Education:
Stony Brook University 2009 - 2010
Master of Science, Masters, Computer Science Rv College of Engineering, Vtu 2003 - 2007
Bachelors R.v College of Engineering
Rv College of Engineering
Skills:
Cloud Computing
Web Services
Machine Learning
Data Mining
Strategic Planning
Marketing Strategy
Competitive Analysis
Java
Sql
Project Management
User Experience Design
User Research
Databases
Project Planning
Distributed Systems
Statistical Data Analysis
A/B Testing
Metrics Definition
Growth Hacking
Public Speaking
Business Strategy
Brand Development
Mobile Applications
Search Engine Ranking
Search Engine Technology
Relevance
C++
Software Development
Software Engineering
Agile Methodologies
Algorithms
Scrum
Karan Rekhi Photo 2

Karan Rekhi

View page

Publications

Us Patents

Rule-Based Machine Learning Classifier Creation And Tracking Platform For Feedback Text Analysis

View page
US Patent:
20220366138, Nov 17, 2022
Filed:
May 17, 2021
Appl. No.:
17/322720
Inventors:
- Redmond WA, US
Christopher Lawrence LATERZA - Issaquah WA, US
Manoj KUMAR RAWAT - Bellevue WA, US
Karan Singh REKHI - Sammamish WA, US
Natarajan ARUMUGAM - Bothell WA, US
Pranav Jayant FARSWANI - Seattle WA, US
Assignee:
Microsoft Technology Licensing, LLC - Redmond WA
International Classification:
G06F 40/279
G06N 20/00
G06F 16/35
G06F 16/33
G06F 16/338
Abstract:
A system and method for creating a machine learning (ML) classifier for a database uses a weakly-supervised training data set created automatically from database items on the basis of a human-created keyword set. The automatically created training data set is used to construct one or more deep learning classifier checkpoints, which can then be compared with one another and with a classifier based on the original keyword set in order to select a classifier for use by other users viewing the database.

Rule-Based Machine Learning Classifier Creation And Tracking Platform For Feedback Text Analysis

View page
US Patent:
20220366139, Nov 17, 2022
Filed:
Jun 23, 2021
Appl. No.:
17/356122
Inventors:
- Redmond WA, US
Christopher Lawrence LATERZA - Issaquah WA, US
Manoj KUMAR RAWAT - Bellevue WA, US
Karan Singh REKHI - Sammamish WA, US
Natarajan ARUMUGAM - Bothell WA, US
Pranav Jayant FARSWANI - Seattle WA, US
Assignee:
Microsoft Technology Licensing, LLC - Redmond WA
International Classification:
G06F 40/279
G06F 16/338
G06F 16/35
G06N 20/00
G06F 16/33
Abstract:
A system and method for creating a machine learning (ML) classifier for a database uses a weakly-supervised training data set created automatically from database items on the basis of a human-created keyword set. The automatically created training data set is used to construct one or more deep learning classifier checkpoints, which can then be compared with one another and with a classifier based on the original keyword set in order to select a classifier for use by other users viewing the database.

Predicted Travel Intent

View page
US Patent:
20170211945, Jul 27, 2017
Filed:
Apr 7, 2017
Appl. No.:
15/482185
Inventors:
- Redmond WA, US
Karan Singh Rekhi - Bellevue WA, US
Gautam Kedia - Bellevue WA, US
Assignee:
Microsoft Technology Licensing, LLC - Redmond WA
International Classification:
G01C 21/34
G06N 5/04
G06N 99/00
G01C 21/36
G06F 17/30
Abstract:
One or more techniques and/or systems are provided for providing a recommendation and/or a travel interface based upon a predicted travel intent. For example, a set of user signals (e.g., search queries, calendar information, social network data, etc.) may be evaluated to determine the predicted travel intent for a user to travel to a destination. A recommendation may be provided based upon the predicted travel intent. For example, images, news stories, advertisements, events, attractions, travel accommodation (e.g., hotel, car, and/or flight reservation functionality) and/or other information and functionality associated with the destination may be provided through the recommendation. The recommendation may be provided through an alert, a mobile app, a website, a travel interface, and/or a variety of other interfaces. The predicted travel intent may be used to modify information provided by a website, an operating system, and/or apps (e.g., a news app may display information about the destination).

Identification And Presentation Of Changelogs Relevant To A Tenant Of A Multi-Tenant Cloud Service

View page
US Patent:
20170032268, Feb 2, 2017
Filed:
Jul 31, 2015
Appl. No.:
14/815833
Inventors:
- Redmond WA, US
Ricardo Soares Stern - Redmond WA, US
Mufaddal M. Pratapgarhwala - Seattle WA, US
Karan Singh Rekhi - Sammamish WA, US
Bhavin J. Shah - Bothell WA, US
Eddie W.M. Fong - Bellevue WA, US
Nagaraju Palla - Bothell WA, US
Parikshit Patidar - Bellevue WA, US
International Classification:
G06N 7/00
G06N 99/00
Abstract:
Technologies are described herein for identification and presentation of changelogs relevant to a tenant of a multi-tenant cloud service. Change feature extraction is performed on changelogs associated with a tenant of the multi-tenant cloud service to identify features associated with the changelogs. Machine learning based classification can then be performed on the changelogs to classify the changelogs. Misclassification correction might also be performed on the classified changelogs. Machine learning can also be utilized to identify a subset of the changelogs as being relevant to the tenant. A user interface (UI) can then be generated and provided to the tenant that includes the subset of the changelogs. The tenant's interaction with the changelogs presented in the UI can be monitored and data describing the interaction can be used to modify machine learning models utilized for machine learning change classification and for determining the relevance of a changelog to the tenant.

Changelog Transformation And Correlation In A Multi-Tenant Cloud Service

View page
US Patent:
20170034010, Feb 2, 2017
Filed:
Jul 31, 2015
Appl. No.:
14/815799
Inventors:
- Redmond WA, US
Nagaraju Palla - Bothell WA, US
Ricardo Soares Stern - Redmond WA, US
Rajmohan Rajagopalan - Bothell WA, US
Bhavin J. Shah - Bothell WA, US
Narendra Babu Alagiriswamy - Bothell WA, US
Karan Singh Rekhi - Sammamish WA, US
Parikshit Patidar - Bellevue WA, US
International Classification:
H04L 12/24
H04L 29/08
Abstract:
Technologies are described herein for changelog transformation and correlation in a multi-tenant cloud service. Components within the multi-tenant cloud service generate changelogs that describe changes made to hardware or software components within the multi-tenant cloud service. The changelogs are received and transformed from different schemas into a common schema. A central change management service (“CCMS”) exposes a network service application programming interface (“API”), or other type of interface, through which other network services can obtain the changelogs that have been transformed into the common schema. For example, services can obtain changelogs in order to correlate changes to anomalies or other events taking place in the multi-tenant cloud service, to identify upstream or downstream components that might be impacted by a change, to provide a user interface for viewing the changelogs, the correlation, or the potential impact of a change, and/or to perform other types of functions.

Viewport-Based Implicit Feedback

View page
US Patent:
20160350658, Dec 1, 2016
Filed:
Jun 1, 2015
Appl. No.:
14/727026
Inventors:
- Redmond WA, US
Kieran McDonald - Redmond WA, US
Qi Guo - Redmond WA, US
Abhishek Jha - Redmond WA, US
Karan Singh Rekhi - Redmond WA, US
Zachary Kahn - Redmond WA, US
Aidan Crook - Redmond WA, US
Assignee:
MICROSOFT TECHNOLOGY LICENSING, LLC - Redmond WA
International Classification:
G06N 5/04
G06F 3/0481
G06N 99/00
G09G 5/14
Abstract:
Examples of the present disclosure describe systems and methods for improving the recommendations provided to a user by a recommendation system using viewed content as implicit feedback. In some aspects, attention models are created/updated to infer the user attention of a user that has viewed or is viewing content on a computing device. The attention model may be used to convert inferences of user attention into inferences of user satisfaction with the viewed content. The inferences of user satisfaction may be used to generate inferences of fatigue with the viewed content. The inferences of user satisfaction and inferences of user fatigue may then be used as implicit feedback to improve the content selection, content triggering and/or content presentation by the recommendation system. Other examples are also described.

Predicted Travel Intent

View page
US Patent:
20150168150, Jun 18, 2015
Filed:
Dec 12, 2013
Appl. No.:
14/105095
Inventors:
- Redmond WA, US
Karan Singh Rekhi - Bellevue WA, US
Gautam Kedia - Bellevue WA, US
Assignee:
Microsoft Corporation - Redmond WA
International Classification:
G01C 21/00
Abstract:
One or more techniques and/or systems are provided for providing a recommendation and/or a travel interface based upon a predicted travel intent. For example, a set of user signals (e.g., search queries, calendar information, social network data, etc.) may be evaluated to determine the predicted travel intent for a user to travel to a destination. A recommendation may be provided based upon the predicted travel intent. For example, images, news stories, advertisements, events, attractions, travel accommodation (e.g., hotel, car, and/or flight reservation functionality) and/or other information and functionality associated with the destination may be provided through the recommendation. The recommendation may be provided through an alert, a mobile app, a website, a travel interface, and/or a variety of other interfaces. The predicted travel intent may be used to modify information provided by a website, an operating system, and/or apps (e.g., a news app may display information about the destination).

Personalized Entity Preferences Model And Notifications

View page
US Patent:
20140372423, Dec 18, 2014
Filed:
Jun 13, 2013
Appl. No.:
13/916853
Inventors:
- Redmond WA, US
Kyrylo Tropin - Redmond WA, US
Türker Keskinpala - Redmond WA, US
Karan Singh Rekhi - Bellevue WA, US
International Classification:
G06F 17/30
US Classification:
707725
Abstract:
Architecture that performs the automatic modeling of user preferences for entities (a personal entity preference model) based on user's actions such as search history and temporal search behavior to determine content on the web relevant and of interest to a given user at any given time. Explicit and implicit user responses (e.g., notification clicks, ignore, dismiss, unsubscribe, notification dwell) are used to update the model of user entity preferences. The user entity preference model is used to order notifications based on predicted relevance. Additionally, the user personal entity preference model and implicit responses of user are used to decide timing and frequency of notifications.
Control profile
Karan Singh Rekhi from Sammamish, WA, age ~39 Get Report