Data Engineering

TUSHAR RAO

Boston, MA +1-857-***-**** ***.**@************.***

SKILLS

• Languages: Python (Pandas, numpy, matplotlib, BeautifulSoup, selenium, scikit-learn), C, MATLAB

• Data Visualization: Tableau, PowerBI, R, RStudio, Datawrapper, Alteryx, Flourish

• Databases: MS SQL Server, MySQL, PostgreSQL, MongoDB, SSIS, Talend, Toad Data Modeler

• Softwares: Jupyter, Anaconda, Visual Studio, Draw.io, Microsoft Visio, Microsoft Project, Minitab EDUCATION

Northeastern University Boston, MA

MS, Engineering Management, GPA: 3.63/4.00 Expected: June 2021 Coursework: Data Mining, Data Warehousing and Business Intelligence, Data Management and Database Design, Operations Research, Engineering Probability and Statistics, Engineering Project Management

Fr. Conceicao Rodrigues College of Engineering, Bandra Mumbai, India Bachelors, Electronics Engineering June 2019

EXPERIENCE

Data Operations Specialist, Team Robocon CRCE June 2017 - April 2018

• Implemented databases, using SQL Server to store performance data such as launch angle and detected color, wrote queries to find relevant data, resulting in 15% reduction in development time

• Performed data visualization using Tableau, to gather insights on various performance metrics of the robots, which helped speed up fabrication by 20%

• Consulted with outside vendors and sponsors and collected funds amounting to INR 120,000 (around USD 1,700), as a sponsorship coordinator

Engineering Intern, RoboVR Pvt. Ltd. Oct. 2017 - Dec. 2017

• Developed ETL pipelines, performed data cleansing, data transformation and error handling, for data integration, and databases using SQLite

• Conserved about 10% of maintenance costs by performing data visualization and generated reports, using Tableau, to find out major causes for errors and feasible solutions for error rectification PROJECTS

Video Game Popularity Predictor Oct. 2020 – Present

• Collected and cleaned data by eliminating duplicated data samples and filling in missing values

• Currently testing algorithms like k-NN, Naïve Bayes and Random Forest using R to build a predictive model to predict the probability of a video game being a successful release depending on parameters such as launch region, platform, genre/type and more

Lower Back Pain Level Prediction Aug. 2020 – Oct. 2020

• Performed data cleaning by filling missing values, removing duplicate data, and introducing dummy variables

• Created a classifier to classify lower back pain as “Normal” or “Abnormal” based on predictors such as pelvic tilt, Scoliosis slope, sacral slope and so on

• Constructed a predictive model, working with various algorithms such as k-NN and Random Forest using Python and R with an accuracy of 72%

E-Commerce Management System July 2020 – Aug.2020

• Designed and modelled the database, using Toad Data Modeler

• Developed database that follows ACID principles to manage operations like account creation, ordering and shipping

• Performed data integration operations by constructing ETL and ELT data pipelines using SSIS and Talend to load about 1.5 million rows of data from various data sources into the created database Database Design and Development for Steel Plant Maintenance Feb. 2020 – May 2020

• Collaborated with a team of three and provided database architecture, design, and best practices for development

• Developed ETL jobs to populate tables with over 200,000 rows of time series data and created database that satisfies 3NF, in SQL Server

• Performed data visualization using Tableau and R to create reports and show the status of operations for various kilns and repair shops, determined major reasons for faults in boosters and the possible solutions

• Created stored procedures, views and a trigger along with table-level check constraints, non-clustered indexes and computed columns. Performed query optimization, which reduced execution time by around 10%

Contact this candidate