EDUCATION

VRUNDA SHAH

BOSTON, MA ***** add9l1@r.postjobfree.com 617-***-****

https://www.linkedin.com/in/vrunda09/

Northeastern University, Boston, MA Aug 2021

Master of Science in Data Analytics GPA: 4.0

Courses: Engineering Probability and Statistics, Data Mining, Data Analytics, Machine Learning, Data Structure, Data Management Gujarat Technological University, India May 2019

Bachelor of Computer Engineering

Courses: JAVA, Database Management, Python, Analysis Design of Algorithms, Artificial Intelligence, Data Mining and Business Intelligence

Skills

Programming Language: SQL, JAVA, Python, C++, Scala, Spark, R, HTML, C# Visualization tools: Tableau, PowerBI, Jupyter notebooks Database: Server Management, MySQL, MongoDB, Neo4j Cypher, Spark (Sparklyr), Firebase ML Libraries: NumPy, Pandas, TensorFlow, Matplotlib, Seaborn, Scikit-learn, statsmodels Statistical Techniques: Logistic Regression, K-Nearest Neighbors, Naïve Bayes, Neural Nets, Collaborative Filtering, PCA, Classification and Regression Trees, SVM, LDA, K-Means Clustering Microsoft office: Excel, PowerPoint, Word, Visio

Projects

Customer Attrition Analyzing and Prediction, Northeastern University Jan 2020 - Apr 2020

• Analyzed 10 years of telecommunication company’s customer dataset to predict customer attrition and to performed data analysis to find important factors for customer attrition in the team of 2

• Conducted data wrangling and cleaning by omitting missing values and deleting attributes

• Examined data exploration and analyzing through various visualization plots such as bar plots, pie chart, correlation matrix and box plots using RStudio

• Implemented machine learning algorithms such as Regression, Classification, Random Forest, KNN, Neural nets, LDA and Decision Tree to find the best model having accuracy greater than 80% Supply Chain Prediction Jan 2020 - Apr 2020

• Developed Business rules, Entity-Relationship diagram, and relationship between 11 entities for manufacturing firm producing bags

• Collected 3 years of historical data of firm and designed database using MYSQL and MongoDB shell that enables organization to maintain its inventory according to demand

• Displayed the results using PowerBI such has map different states with frequent order, histogram showing month wise selling of each product, line graph depicting August that has maximum selling Renewable Energy Prediction Jan 2020 - Apr 2020

• Explored 70 years of data of renewable, non-renewable energy and carbon emission of United States to find alternative to non- renewable energy for forthcoming years

• Visualized the trend of renewable energy production using seaborn, matplotlib libraries in Jupyter notebooks

• Predicted total renewable energy needed to meet the power demand of United States for next 3 years using Random Forest with accuracy 70.94% in Python

• Implemented time series analysis and constructed Seasonal Arima model to determine total carbon emission over the years and exhibited trajectory for upcoming years

Analysis of Breast Cancer, Northeastern University Sept 2019 - Dec 2019

• Collaborated with 2 other people and performed statistical analysis on breast cancer dataset of 600 occurrences using R and compared major symptoms of Malignant and Benign cancer

• Examined data using visualization techniques to find pattern in cancer tissues using ggplot2 and shiny libraries

• Performed quantitative analysis using hypothesis testing and numerical algorithms to create prediction model for showing that Malignant tumors were more prevalent by 45% than Benign tumors Work Experience

Skynet Computers, India May 2018 - Apr 2019

• Developed android application for transportation services to manage routes, cars and drivers

• Generated shortest Automatic route for the car on entering location with stop points using travelling salesman algorithm implemented in JAVA

• Integrated mobile application with google APIs for generating routes Data Analytics Student Organization, Northeastern University Oct 2019 – Present Secretary

• Collaborate with University sponsorship department for organizing, documenting and reporting of event

• Worked with 10 members to organize Co-op Panel event focused on careers in data analysis