Gurpreet Singh Bhatia ********@*****.***
Education
•
University of Michigan Ann Arbor, MI
Master of Science in Information, Specializing in Data Science May 2021
•
Guru Gobind Singh Indraprastha University Delhi, India Bachelor of Technology, Information Technology.; GPA: 3.76 July 2015 Experience
•
Indraprastha Institute of Information Technology Delhi, India Research Associate Sep 2017 - Aug 2019
Advanced Analytics for Social Media Analysis (AASMA):
{ Key contributor to designing, developing, and maintaining large-scale data mining web application.
{ Scaled the project from 60 to 100+ organizations leading a team 5 developers. [Python, Rails, Apache Storm]
Spam Campaign Characterization:
{ Developed framework to detect and suspend spammers by analyzing over 23 million tweets using Random Forest.
Digital Signals on Stack Over
ow:
{ Identi ed evidence of positive correlation between reputation scores and badges, and social attributes Popularity and Impact of Stack Over
ow (SO) users.
{ Applied Gradient Tree Boosting Regression to model dataset of 3.8 Million users; R 2
(Popularity) = 0.956 and
R
2
(Impact) = 0.858.
•
Sapient Consulting Delhi, India
Associate Software Engineer L1 April 2016 - Jul 2017
Data Integration Middleware Platform:
{ Built Data Integration framework with Publisher / Subscriber format that provides a middleware platform for communication between proprietary systems.
{ Steered development of component for le format conversion using business logic. [ Java Spring, SQL] Projects
• Honda CV Hackathon : Developed application to detect parking spot on the road using Yolov3 and Darknet.
• Newspaper vs Stocks : Empirical analysis of how headlines in
uence stock value of an Indian company for the year 2008. [Hadoop, PySpark, Spark SQL]
• DeepTra c : Utilized Deep Reinforcement Learning to model a car that drives through virtual highway tra c.
• Video Analysis : Added support for Non-GPU servers to poll and execute video functionality on GPU servers in the network using RPyC.
• Track On Twitter : NodeJS application to track keywords on Twitter using Chrome noti cations. Achieves Async I/O using Callbacks and Promises.
Publications
• \Signals Matter: Understanding Popularity and Impact of Users on Stack Over
ow", Short Paper, The Web Conference 2019 (WWW), 20% acceptance. [Link]
• \Under the Shadow of Sunshine: Characterizing Spam Campaigns Abusing Phone Numbers Across Online Social Networks", Journal of Web Science 2019.
Skills
• Languages: Java, Python, C++, Javascript, SQL
Machine Learning: Pandas, Keras, TensorFlow
Tools: Hadoop, Spark, Git, Docker
Frameworks:MongoDB, NodeJs, Spring MVC
Courses
• Computational Data Science and Machine Learning, Data Manipulation, Algorithms, Computer Networks, Operating Systems
Working towards a graduate degree in computer science, computer engineering or related discipline • Experience in one or more of C++, Java, Scala, Python or equivalent programming language • Understanding of advanced data structures and algorithms • Familiarity with linear algebra, statistics, information theory or related mathematical domains • Understand deep learning, dynamic programming, reinforcement learning or related areas • Ability to develop and execute processes for complete CI/CD pipeline • Excellent written and verbal communication skillS Preferred Requireme