Data Assistant

Sunakshi Sharma

Email: ********.********@*****.*** GitHub: https://github.com/CoderChick16/ Current Residence: San Francisco Bay Area, CA Education

Rochester Institute of Technology, New York, USA, GPA: 3.9/4 Master of Science, Information Sciences and Technologies, Aug 2017 – May 2020

• Relevant Coursework: Data Driven Knowledge Discovery, Data Mining, Visual Analytics, Information Retrieval, Knowledge Representation Technologies, Data-Warehousing, Geographic Information Systems, Statistical Analysis for Decision Making Maharshi Dayanand University, Haryana, India, GPA: 71.4% Bachelor of Technology in Computer Science and Engineering, Sep 2009 - May 2013

• Relevant Coursework: Data Structures and Algorithms, Analysis and Design of Algorithms, Operating Systems, Theory of Automata, Discrete Structures. Academic Research Experience

Rochester Institute of Technology, Rochester, New York Research Assistant - Aug 2018 – Jan 2019

• Assisted professor to direct research towards optimizing the execution and designing a cube over big data to handle unstructured data as well.

• Constructed a data warehouse of structured and unstructured data using Natural Language Processing, building topic models and applying unsupervised learning. Surveyed techniques like LDA, PLSA, LSA, tools and frameworks like pyLDAvis, Gensim and metric to choose the hyper-parameters like coherence values and plots. Work Experience

Rochester Institute of Technology, Rochester, New York Graduate Teaching Assistant – August 2019 – December 2019

• Responsible for clarifying students doubts related to Data Cleaning, Transformation and loading process in the overall data mart creation and grading the assignments.

• Topics like Slowly changing dimension, Dimensional data modeling, the extract/transform/load process, warehouse implementation, dimensional data analysis, and summary data management are also been taught in the TA hours assigned. eLogic LLC, Rochester, New York

Data Scientist - Internship - Jan 2019 – May 2019

• Developed a recommendation engine to be able to recommend products for major manufacturing companies selling products through online channels. The product recommendation engine improved precision@k by 11.6% and click through rate by 7%.

• Developed analytical dashboards using Power BI for one of the major manufacturing company to analyse their overall sales and revenue across verticals. The dashboard would be used to provide analytical and quantitative insights.

• Built data-pipeline to store, provide structure for the purpose of analytical queries and address data quality issues by transformation of data collected through web- scrapper. The pipeline as a framework further helped in streamlining unstructured data across the organization. Infosys Limited – Pune, India

Senior Software Engineer – Full-time, Feb 2014 – Jul 2017 Operation Excellence Management System (P&G)

• Automated data fetching using SAP GUI and report generation in formats like excel and pdf, creating stored procedures and writing complex SQL queries for large data-sets.

• Created DTSX Package using SQL Server Integration Services (SSIS) for various processes on daily basis. Worked on Win-Shuttle Tool to extract data from SAP, maintain and develop functionalities.

• Automated various process development modules as required, carried out unit testing, take client calls and analyse business requirements. Technical Skills

• Languages: Python, R, C#, SQL

• Web Technologies: Flask, Node.js, Express.js, JavaScript, HTML, CSS, REST, AJAX

• Big Data Technologies: AWS EMR, Hive, Presto

• General: Data Structures and Algorithms

• Databases: MySQL, MongoDB, Neo4j

• Tools: Weka, R-Studio, Anaconda, Tableau, Pentaho, ArcGIS, Power BI Projects

• Predicting Credit Card Default: Banks often issue credit cards to ineligible customers without adequate background checks. Many customers use their credit card beyond their repayment capabilities leading to high debt accumulation. In this project, we are trying to analyze how to identify the risky and non-risky customers, helping the bank to decide if a customer has the potential to repay the used credit of the bank. View Project: https://shorturl.at/fpvBI

• Analysis of Black Friday Market Trend Using Visual Analytics: Performed visualization of the data in pursuit to be able to analyze consumer trends during black Friday. View Project: https://shorturl.at/aflpP

• Toronto Crime Analysis using Hotspot Analysis and Crime Mapping Analysing the crime in Toronto. Using GIS tool analysis was based on crime rate based on location, time of the day and reasons that could have caused those crimes. View Project: https://shorturl.at/cuzMY

• Full-Text Search Engine: Created a full-text search capability for searching the hotels using Node.js, MongoDB and AWS using dataset from Kaggle. View Project: https://shorturl.at/kuEH4

• Sentiment Analysis of Mobile App Reviews: Performed sentiment analysis on mobile app reviews given by the users. Prediction based on various factors determine the class value of a review being positive or negative in future.

• Data-Warehouse: Built a full fledge Data Mart using ETL (Extract, Transform and Load) operations and Pentaho as a tool which is responsible for the analysis of the sales of products to the customers, suppliers along with the calculation of revenues on a daily, weekly, monthly, quarterly and yearly basis through sale date and order date.

Achievements

• Awarded with 80% scholarship on tuition for stellar academic performance and Research Assistantship at Rochester Institute of Technology.

• Spot award for best performer at Infosys Limited.

Contact this candidate