
PhD student at SUNY Stony Brook
Bombay Area, India

PhD student at SUNY Stony Brook
Bombay Area, India
Publications:
- An exploration of pages with high betweenness centrality on the World Wide Web: searching with inexact queries (Int. Conf. on Social Network Analysis and Applications, '09)
Work:
1. Data Mining and Natural Language Processing :
* Worked on Weka.
* Building an automated opinion-based classifier of web documents (news and UGC).
* Noise Elimination and Automatic identification of relevant portions of web-pages.
* Automatic detection of opinion holder from content.
2. Machine Learning Algorithms (all the following were implemented to be scalable to any extent):
* Naive Bayes Classifier
* Support Vector Machines (SVM)
* Hybrid SVM classifiers
* Decision Tree Learners: ID3, C4.5
* k-nearest neighbor (kNN)
3. Built an automating and a testing software for machine learning algorithms. (Think of it as Weka without GUI and without constraints on data size!)
4. Web Crawler: Involves ranking index, horizontal scalability, relevant content extraction, politeness, among several other issues.
5. Algorithm design for process/task automation : Built an automating software for generation of financial reports.
* Algorithms: Natural Language Processing, Data mining, Machine Learning.
* OO Design. Completely language-agnostic. Expertise in Ruby, Perl, Java.
(Educational Institution; Higher Education industry)
August 2009 — Present (4 months)
(Information Technology and Services industry)
March 2008 — May 2009 (1 year 3 months)
Machine Learning, Nautral Language Processing, Data Miining, Database design.
(Privately Held; 51-200 employees; Information Technology and Services industry)
June 2007 — April 2008 (11 months)
Automate everything under the sun! Anything that can be done by machines should not be done by humans . . . so I was busy building software modules that render human beings redundant.
(Privately Held; Information Technology and Services industry)
February 2007 — June 2007 (5 months)
Natural Language Processing and development of vertical net crawler. Making good use of Web 2.0!
Generation of a mathematical model involving linguistic variables. Worked at the algorithm design level as well as at the software production level.
(Privately Held; Marketing and Advertising industry)
May 2006 — July 2006 (3 months)
Natural Language Processing and Non Linear Optimization.
Worked in a small technical team implementing a search engine marketing tool called Broadwords (copyright lies with the organization). Worked at the algorithm designing level as well as at the software production level.
M.Sc. , Computer Science , 2005 — 2007
B.Sc. , Mathematics , 2001 — 2004
Web 3.0, Algorithms, Investing, New Technology, Literature, Theater, Poetry, Trekking