Dallas, Texas Tel: +1-469-***-**** firstname.lastname@example.org http://www.utdallas.edu/~kjm160030/ Education:
The University of Texas at Dallas, Richardson, Texas Masters in Computer Science GPA: 3.701 May 2018
Coursework: Statistical Methods of Data Science, Database, Machine learning, Algorithms, Artificial Intelligence, Big Data and Analysis, Data Representation, Object Oriented Design and Analysis, Computer Vision VESIT, University of Mumbai, Mumbai, India
Bachelor of Engineering in Information Technology Aggregate: 72.2% June 2015 Relevant Coursework: Data Structures & Algorithms, Game Programming, Internet Programming, Operating Systems Technical Skills:
Languages : C++, Java, R, Scala, Python,
Operating Systems : Linux, Windows
Database : MS SQL, MySQL, Oracle, ElasticSearch
Viral MD Data Science Intern Aug 2017-Dec 2017
• Converted the scanned document PDF to XML using the OCR and developed scripts in Python to query the XML by converting it into element tree in to query the required information using MySQL server using Etree and SQLAlchemy libraries.
• Used Naïve Bayes algorithm to classify the document with an accuracy of about 82%. Accenture Services Pvt. Ltd Software Engineer July 2015 - June 2016
• Development of scripts, plugins for Oracle Fusion Middleware and Master Data Management Systems using Java and Oracle
• Debugging and code fix of the utilities application using JUnit and HPE LoadRunner. Academic Projects:
Blood Donation Prediction(Python)
• A machine learning project in python for predicting the probability for a person donating blood. Used the Artificial Neural Network to build a model that will predict the donation probability. An accuracy of 80% was achieved. 9 Men Morris Game (Java)
• This is a two-player game developed with an artificial intelligence in Java.Used the MiniMax and Alpha Beta Pruning algorithms to determine the next move of the system in the game. Analysis of inter-relation between interstate migration, fatalities & unemployment (Fuseki,SPARQL)
• This is a semantic web application using dataset of interstate migration, fatalities & unemployment to find the co-relation between the data using Jena API and Apache Jena Fuseki server to run SPARQL query over HTTP.Used the Google visualization APIs to represent the results obtained from the SPARQL queries. Sentiment Analysis of Tweets (Java, Elasticsearch, Kibana )
• A Big Data project to visualize sentiment analysis of tweets through Tile Map as per geo Locations of tweets based on given hashtag/topics on Kibana via Spark Streaming using Elasticsearch,
• Scrapping tweets was done in java through twitter4j API using zookeeper and kafka and Stanford NLP library to perform sentiment analysis on the tweets scrapped.
Prediction of Airline Delays Using Machine Learning Techniques (Scala, Python, Hadoop)
• A big data management project for predicting airline delays using Liner and Logistic regression technique for an airport and for a route. Also performed comparative analysis of historic data of airline database to find the trend in flight delays like in days of months, months with maximum delay, carrier with maximum delay etc. Domain Name Database Management System (HTML, CSS, Node.js, Oracle Database)
• A web mining project which provided the functionality of providing real time feedback and reviews on electronic gadget requested by the user. Used Phirehose PHP library for extracting tweets from Twitter and Naïve Bayes Classifier to perform sentiment analysis.
All Secure (Java, JavaSwing, SQL Server 2008.)
• Data security project aimed to transfer data in a communication network with the help of dynamically changing encryption algorithm. The project included the functionality of steganography and PDF security. Achievements:
• Awarded Star Performer at Accenture for taking ownership of testing and debugging of the major functionality and increasing the accuracy to around 70%
• 1st position in Technical Paper Presentation at technical event PRAXIS 2013 for ‘Cyber Forensics’ at VESIT.