I'm pursuing Master of Science(M.S) in Computer Science at University of Texas at Dallas.I have a strong background in data structures & algorithms, OOP concepts and hence in designing architecture. I am familiar with full-stack product development, backend frameworks.
I have experience in working with Machine Learning and Big Data Tools and Technologies. My knowledge in this field includes: data preprocessing, feature extraction and selection, time series forecast, clustering, regression/classification prediction, association rules mining.
I'm currently in my final semester at UT Dallas. I'm actively looking for a Sofware Development positions starting from August 2018.
I like to code, build software and tools that make life effortless. I thoroughly enjoy learning new technologies that enable me to create more compelling work.
GPA: 3.7
GPA: 3.6
Implemented a semantic search application that will produce improved results using NLP features and techniques. A corpus of FAQs is taken where Keyword search index creation is done followed by Natural language query parsing and search. It is followed by implementing a deeper NLP pipeline to perform Semantic search index creation and then Natural language query parsing and search.
IAn e-commerce web application for an online mobile store. The website has all the features that are expected in a modern e-commerce website viz, User Registration, User Authentication, Cart and checkout functionality, maintaining the buyer history, Smart Search, Admin Privileges to maintain products(CRUD).
Scripted a Scrapper program in Python to collect tweets in real-time with particular hash-tags and send tweets filtered on latitude and longitude to Apache Kafka API and performed Sentiment analysis. Timestamped output for each hash-tag and sent to Elasticsearch. Built Kibana dashboards to display visualizations in Elasticsearch indices.
Scripted a Scrapper program in Python to collect tweets in real-time with particular hash-tags and send tweets filtered on latitude and longitude to Apache Kafka API and performed Sentiment analysis. Timestamped output for each hash-tag and sent to Elasticsearch. Built Kibana dashboards to display visualizations in Elasticsearch indices.
Implemented a recommender system for a user using ALS Collaborative Filtering techniques and modified it as a web application using Flask. 48 million reviews meta-data from Amazon is taken as dataset.
Created a manual Database engine that is similar to MySQL and optimized the run time of query processing by implementing the concepts of Indexing using efficient data structures.
A comprehensive web application for free and for sale portal that allows students to buy and sell goods within their community.
Programmed and developed Decision Tree (ID3), Neural Net (Back Propagation), Naive Bayes Classifier and customized them to increase the test accuracy on various datasets available online.
Implemented a model to identify duplicate questions by applying Ensemble techniques to classify whether question pairs are duplicates or not based on semantic similarity and achieved a log loss metric as 0.34 on 2.4 million test tuples.
Question classification is done using Support Vector Machine(Li-Roth based classifier) and then Google web search API is used for Answer Retrieval. Finally to extract named entities, used Stanford Named Entity Recognizer.
Apart from being a graduate student, I enjoy most of my time travelling with friends and exploring new places. I like playing soccer and cricket.
I spend a large amount of my free time exploring the latest technolgy advancements in Machine Learning, Natural Language Processing, and I follow a number of sci-fi and fantasy genre movies and television shows, I am an aspiring chef.