Puneet Singh Ludu

Programming

• Advanced knowledge of Java, C, Perl, HTML
  
• Good knowledge of C++, C#, Python, PigLatin
  
• Basics of PHP, jQuery, JavaScript, CSS, Matlab
  

Skills

• Advanced algorithms and data structures
  
• Distributed computing (Apache Hadoop, Apache Pig, Apache Spark, PredictionIO)
  
• I know: Git, Eclipse, Sublime, Svn. (and many other tools)
  

University projects

• Inferring gender of a Twitter user using celebrities it follows (Java, Perl, Google API, Apache Pig)
  
• Quena- An automatic question answering system (Java, Apache Solr, Stanford NER, Stanford POS tagger, web crawler)
  
• Clustering of songs files according to mood derived from signals and lyrics (Matlab, Perl, C#)
  
• English to Hindi Translation and Transliteration (C, Gambas) [Natural Language Processing]
  
• PSLFS – Virtual File system, based on the K-Ary Data Structure with a Command Line Interface (C)
  
• Amazon Dynamo algorithm- replicated key-value storage (Distributed systems, Java)

Personal projects

• Memodiction - An Android app that lets you learn and revise words to build your vocabulary intelligently
• Tweetiments.com - Sentiment Analysis of Twitter data (Perl, PHP)
  
• HappyOrSad - Perl script to know mood of text and lyrics (https://github.com/puneetsl/HappyOrSad)
  
• ShortCleaner - A JAVA library to clean tweets for consuming it for various kinds of analytics.
  
• jTextBrew - A JAVA library for fuzzy string matching, based on TextBrew algorithm by Chris Brew.
• Reviewed 5 chapters of "Apache Solr Essentials" (http://goo.gl/Q7h3mW)

Conferences and Publications

• "Inferring latent attributes of an Indian Twitter user using celebrities and class influencers", ACM Hypertext 2015
• "Architecture for Automated Tagging and Clustering of Song Files According to Mood", IJCSI, 2010
  
• "Inferring gender of a Twitter user using celebrities it follows", CSE Dept, University at Buffalo, 2014
  
• "PSLFS: Command Line Interpreter and Virtual File System", ICCC, 2008.

Experience

NLP Engineer, April 2015 - Present, Factset Research Systems – New York City

• Duplicate document identification (Java, Shell Scripts)
  • Used Shingling and Vector Space Model algorithms to detect duplicate documents from a stream of documents.
• Statistical Machine Translation (Moses, Python)
  • Building a language translation engine similar to google translate, for Polish, based on principles of statistical machine translation.
  • The cleaning, tokenization, stemming and other language processing is done by using nltk and other NLP libraries in python.
• Earning and Stock Correlation using Social Media Sentiments (Python, Java, PredictionIO)
  • Exploratory project to find correlation between social media sentiments with earnings and stocks of a company.

Research Engineer, July 2011 - July 2013, Innovation Labs, TATA Consultancy Services – Delhi

• Time Series Analysis on Big Data : (Technology and Tools used: Java, Python, Perl, Shell Scripts, Rapidminer)
  
  • Worked on a research project involving multivariate time series analysis of car sensor data.
    
  • Devised an algorithm based on Shape Context for finding frequently occurring patterns and events, with as good results as SAX, DTW etc. with 7% better results in the particular domain of car sensors.
    
• Data Harmonization Framework (DHF) : (Technology and Tools used: Java, Apache Pig, XML)
  
  • Implemented an ETL framework that exploits power of map-reduce and big-databases to fuse incongruous enterprise data from disparate sources in near real time.
    

Developer, December 2010 - June 2011,ILP training centre, TATA Consultancy Services – Trivandrum

• Trainee Evaluation System: Lead team of two, into the development of 'Trainee Evaluation System' as a part of Moodle plugin, deployed in TCS Trivandrum training centre. (PHP, MySql, jQuery)
  
• Resource planning and Scheduling system: Developed solution for managing infrastructure resources and scheduling lectures. (PHP, MySql)
  

Education

Master of Science in Computer Science; State University of New York, Buffalo GPA: 3.482, 2014
Bachelor of Technology in Computer Science; Jaypee Institute of information Technology, Noida, 2010

Research Interests

• Time Series Analysis
  
• Music Information Retrieval
  
• Sentiment Analysis
  
• Web Data mining
  
• Social Network Data Mining
  

Contact

"pludu [at] buffalo.edu" | +1-(716) TOP-HEGG | My personal website