JAY CHOKSI
** ************ ******, ******, ** ***15 857-***-**** ******.*@*****.***.***
EDUCATION
Northeastern University, Boston, MA December 2019
Master of Science in Information Systems
Coursework: Advance Data Science and Architecture, Machine Learning in Finance, Database Management and Design, Designing Data Architecture and Business Intelligence, Big Data Systems and Intelligence Analytics
Mumbai University, Mumbai, India June 2017
Bachelor of Engineering in Electronics and Telecommunications
Coursework: Object Oriented Programming
TECHNICAL SKILLS
Programming Languages: Python, R, SQL, Java
Databases: MS SQL Server, MySQL, Oracle 11g, PostgreSQL, Mongo DB
Cloud Technology: Microsoft Azure, Google Cloud Platform
Tools: Alteryx, Talend, Tableau, Power BI, Qlik Sense, Apache Spark, Apache Airflow
WORK EXPERIENCE
Boston Consulting Group, Boston, MA January 2019- June 2019
Data Science Co-op
•Conducted cleaning process automation of retail survey data in Python, Alteryx and created interactive dashboards in Tableau to enhance business process transformation which led to saving 40 hours of manual work
•Performed correlation analysis on a pharmaceutical company’s quarterly product sales data using Python helping boost a region-specific digital marketing campaign in France by 20% overall increment in sales
•Collaborated with a team of consultants for a client’s Merger to construct visualizations in Tableau and perform the integration of personnel and platforms of merging organizations
•Constructed views on domestic airlines’ data in SQL Server based on ad-hoc requests to perform Geo- analytics in Tableau
•Identified differences in file contents in multiple folders by writing a Python script and increased efficiency by 70%
•Assembled scanned text image data and wrote a python script to perform Optical Character Recognition (OCR) with 75% accuracy
Camp Mobile- BAND, Mumbai, India February 2016- August 2016
Data Analyst Intern
•Collaborated with acquisition team to analyze customer acquisition metrics and reduced cost per install by 20%
•Formulated content marketing campaigns improving user retention by 80% and return visitor conversion by 30%
•Implemented target marketing and AB tested product features increasing engagement by 130%
•Presented weekly reports to the executive team highlighting the Key Performance Index (KPIs) of ongoing strategies
ACADEMIC PROJECTS
Northeastern University, Boston, MA
Cryptocurrency Trading using Machine Learning (Python, Tableau) September 2018- December 2018
•Analyzed Bitcoin time-series data and implemented techniques like MACD, RSI to find Bull and Bear Markets
•Forecasted future prices implementing Linear Regression Model and Bollinger Bands to formulate a trading strategy for maximizing profit when traded in that time range
Data Integration and Business Intelligence (Talend, SQL, Tableau, PowerBI) June 2018- August 2018
•Designed a multi-dimensional data warehouse of size 40 GB working on Talend that integrates data from multiple source of records (PostgreSQL, MySQL, SQL Server, Flat Files, Oracle Server)
•Implemented slowly changing dimensions, Associative Tables, Outriggers in the warehouse and collected job statistics
•Created interactive dashboards in Tableau and Power BI to graphically represent the performance trends
Breast Cancer Detection and Analysis (R, Python, Azure ML, Airflow, PowerBI) January 2018- April 2018
•Constructed a Data Pipeline using Airflow to automate scraping, combining, cleaning and loading the data to blobs
•Built Prediction model using Random Forest and Classification model using Decision Forest and SVM on Azure ML
•Designed insightful dashboards by conducting data analysis using Power BI
Million Songs Database (Python, SQL, Mongo DB, SQLite3, Twitter API, YouTube API) January 2018- March 2018
•Extracted 20k tweets from Twitter and data regarding 5k users profiles on YouTube as a part of data collection using Python
•Converted the SQL database into a NoSQL database using Studio 3T and wrote a detailed portfolio on the conversion
•Conducted raw sentiment analysis and answered real world analytical questions by using MS SQL Server queries