Data Analyst

SHRESHTH YASH

Boston, MA 716-***-**** ************@*****.*** GitHub

Analytical professional with 3 years of experience to analyze business problems and strategic mindset towards data driven solutions on various platforms like big data and cloud technologies EDUCATION

Master of Sciences, Analytics (Data Analytics, Statistics) Northeastern University, Boston, MA Sep 2018 - Apr 2020 Bachelor of Technology G L Bajaj Institute of Technology, Noida, India May 2010 - June 2014 WORK EXPERIENCE

Research Data Analyst Northeastern University Boston, MA May 2020 - Present

• Collecting data from multiple sources via API, web scrapping (Beautiful soup), govt agencies and storing in S3 using Python

• Data Mining and cleaning hospital, prison, nursing home data and 2020 elections data to analyze government policies

• Used Python libraries for predictive analytics regression techniques with hyper parameter & performance metrices

• Designed Tableau dashboards comparing best to worst performing states with Covid polices and 2020 general election Graduate Assistant Disability Resource Centre Northeastern University Boston, MA Mar 2019 – Mar 2020

• Automated training process to online blackboard for 350+ note takers to expedite hiring process by 40 percent

• Designed 3 custom reports from note takers Access db for DRC management & assisted students for mid-term & finals exams

• Performed end to end hiring process through Salesforce generating requests to data extraction and loading in Access DB Software Engineer EXL Services Noida, India May 2017 - July 2018

• Created User stories in Jira with Confluence containing business requirements and wireframes for web LifePro application

• Collaborated with insurance experts from LifePro and modified requirements for application led to saving time by 20%

• Generated data in SQL by issuing 100+ insurance policies in Annuities, Life and Health for use cases in LifePro application

• Worked extensively in understanding the business rules, data requirements and writing requirement specs, technical specs and mapping documents from staging to data warehouse, data mart, and reporting needs to the end user clients

• Accomplished first phase of LifePro web application with 25 modules delivered within 6 months according to road map

• Systemized 3 functional teams Jira & derived data and publish multiple performance reports on Tableau to senior leadership Sr. Software Associate NTT Data Services Noida, India June 2015 - Apr 2017

• Planned and delivered 3 functional modules along with complex module of maintain transaction presented to client

• Developed SQL queries in MySQL server to obtain and clean data for 10 functional modules in members app

• Conceptualized in depth data analysis and designed Tableau dashboard for Events and Membership offered by AQHA

• Moderated Use cases for changing requirements on Jira and orchestrated to functional teams and performed UAT to client

• Mentored methodologies and switched to agile environment in 3 months; led to deep understanding of SDLC and scrum

• Programmed ETL workflows using SSIS to perform source to target data mapping for entire data warehouse with relational databases like MySQL Server

SKILLS & COMPETENCIES

Languages: - R, Python, SQL

Analytics and ML: - Data Mining, EDA, NLP, Predictive Modelling (Regression, Classification and Clustering), Google Analytics Database and BI: - Microsoft SQL Server, Databricks, Mongo DB, Access DB, PowerBI, Tableau, Excel Techniques: - Web scrapping, ETL, Big Data (Hadoop, Spark), Agile, Requirement Gathering (BRD), UAT, RShiny, Scrum, Kanban Tools: - Confluence, Jira, SoapUI, QC, ALM, Alteryx, Docker, RStudio, PyCharm, JuypyterNB Cloud Services: - AWS S3, Glue, Lambda, DynamoDB, RDS, EMR, Athena, Quick Sight, Redshift ACADEMIC PROJECTS

Lending Club Analysis (Azure, Databricks, SQL, PySpark) Medium Feb 2020 - Apr 2020

• Analyzed different grades of customers with various account types for over 3 years of data using Databricks Spark platform

• Used SQL and PySpark with different data formats to perform data wrangling and creating robust data pipeline

• Performed exploratory data analysis with respect to loan status for 4 million customers with various features using Databricks features of visualizations

Predictive Analytics for Brazil Hospital (Python, Scikit learn, NumPy, Pandas, Matplotlib) Medium link Apr 2019 - Jun 2019

• Implemented Machine Learning Classification algorithms on Brazil hospital appointment data to check patient will show up for appointment or not and concluded, 29% of patients will not show up in hospital using scikit learn library

• Enhanced performance by 2% by implementing Feature Selection and Hyperparameter Tuning on selected models

• Evaluated performance using Confusion Matrix, Classification Report and AUC as parameters and outlined learning curve

Contact this candidate