TARAN
GILL
***********@*****.***
tarangill04
á
§
X Vancouver
â
Skills
LANGUAGES
Python
SQL
HTML
Spark
DATABASES
Cassandra
PostgreSQL
Oracle
HADOOP ECO SYSTEM
Hadoop
HDFS
Map-Reduce
YARN
VERSION CONTROL AND
TASK MANAGEMENT
Git
JIRA
Confluence
TOOLS & IDE
Tableau
Jupyter
Spyder
PYTHON AND MACHINE
LEARNING LIBRARIES
Scikit Learn
Pandas
Numpy
NLP Toolkit
Dedupe
Spark ML
TextBlob
Matplotlib
SOFT SKILLS
Excellent Written and Verbal
Communication Skills
Problem Solving
Active Learning
Critical Thinking
Decision Making
Self Motivated
Ability to Work Under Pressure
Results Oriented
Education
Simon Fraser University
Masters (M.Sc.) Computing Science, Big Data Program 2018 University of Fraser Valley
Bachelors (B.C.I.S.) Information Systems 2015
Panjab University, Guru Nanak Girls College, Punjab, India Bachelors (B.Sc.) Computing Science 2009
Employment
Blackduck Software by Synopsys Burnaby, BC
Data Scientist Apr 2017 to Current
Collaborated with team members to optimize Hub database for over 6 million open Source projects and learned a classification model using Classification and Regression Trees Improved model accuracy by 20% using scikit-learn's parameter tuning and reduced training time by 50% by feature engineering
Performed Data analysis and predictive modeling including entity resolution using Word2Vec, TFIDF and Jaccard similarity and decreased the duplicate projects in database Williams Machinery Surrey, BC
Service Writer (Summer Position) May 2016 to Aug 2016 Maintained data log of technician times in a timely manner to maximize productivity Generated Service reports, repair estimates
Positive and professional communication with customers to ensure customer satisfaction Windset Farms Delta, BC
Data Entry Clerk Jul 2013 to Jan 2016
Issue produce orders using "Famous" Software for Safeway, Costco and Loblaws Handled product prices, product transfers to and from US, Spain and Mexico Projects
Learning a Classification model, Blackduck Software Jan 2018 to Current Developing a predictive modelling technique for extremely imbalanced data to identify true duplicate projects based on certain features
Minimize false negatives and reduce the need to manually review projects Process includes feature engineering, parameter tuning, ensemble methods, adjusting class distribution of dataset using undersampling and over sampling methods
Personalized Restaurant Recommender, Big Data Programming, SFU Apr 2017 Built a tool to recommend personalized date locations based on social media sentiment Built user profile by analyzing Yelp reviews. Used Collaborative filtering to make recommendations based on user preferences
Predicted Person of Interest, Big Data Programming, SFU Dec 2016 Predicted the likelihood of being person of interest in Enron fraud conspiracy Python and Spark were used for statistical model training. Volunteering
Helping with the elderly for EI benefits, Visa applications Jan 2012 to Current Newton, Surrey, BC
Opportunities for the Disabled Foundation Data Entry Clerk Oct 2012 to Jan 2013 Burnaby, BC
Major Achievements and Awards
Best Trainee and consistently selected by the customers over other Data Entry Clerks to do order adjustments
(Sept. 2013- Jan. 2016)
Graduated with Distinction from Punjab University (Apr. 2009) Best Student Award (July 2007 & 2009)
Master of Ceremony at several functions at Guru Nanak Girls College (July 2006- Apr. 2009)