About Me

I am a Data Science enthusiast and a graduate research assistant from Northeastern University looking for full time opportunities. In addition, I enjoy storytelling with data and statistics. Previously, I have worked on several deep learning, machine learning and business intelligence based projects as a part of my research work at Northeastern University as well as my tenure at Cognizant Technology Services and Boston Children's Hospital. My research experience with United Nation Development Program motivated me to work on projects which can use data for social good.

I’m always happy to chat about data science and related topics. If you’d like to contact me, please use the following form, or drop me a line via Linkedin or Twitter. Apart from the data deluge, I am into travel and writing. If you share a passion for these two, lets catchup and have a coffee.

Download Resume

Skills

95

R

85

Python

90

Machine Learning

90

Business Intelligence

85

Data Integration / ETL

80

Web Design

Portfolio

Go to GIT Repo

IBM HR Analytics Employee Attrition & Performance

Predict attrition of your valuable employees
IBM HR Analytics Employee Attrition & Performance: Using Deep Learning - Keras Library
See Tableau Public

Global Gross Domestic Production Heatmap

Tableau BI Stories
Global Gross Domestic Production Heatmap: Data Story with Heat Maps
Go to GIT Repo

Prudential Life Insurance Assessment

A predictive model that accurately classifies risk using a more automated approach
Prudential Life Insurance Assessment
Go to GIT Repo

Deep learning Keras-Model over-Semeion Image Data

Implemented Keras Machine Learing algorithm to develop a deep net trained on the test data
Project Title

Adventure Works Business Intelligence Data Story on Sales Segmentation

Developed Pi distribution plot, geomap and barplots
Adventure Works Business Intelligence Data Story
See Tableau Public

Bit Coin Value Time Series prediction using LSTM-Deep Net

Used LSTM based time series model
Bit Coin Value Time Series prediction using LSTM-Deep Net
Go to GIT Repo

Crime Against Women Data Story

Tableau data story displaying statistical analysis on crime against women
Crime Against Women- Data Story
See Tableau Public

Project Title

Web Design
Project Title

Some Stats

130

BI Dashboards

22000

Hours of Work

14

Data Science Projects

2

Years of Experience

Experience

  • Jan 2018
    -
    April 2018

    Northeastern University Business School

    Reserach Assistant

    • Cleaned textual data (around one million records) and performed data munging by transforming and mapping different files provided by IRS
    • Performed text mining on financial data based files using SAS and Python using NLTK and Pandas

    Skills : R, SAS, Python, NLTK, Pandas, Google Cloud

  • July 2017
    -
    Dec 2017

    Boston Children's Hospital

    Data Analyst COOP

    • Followed agile development methodology on daily basis to perform data analysis and resolve support issues
    • Created interactive MicroStrategy dashboards, reports, visual user manuals and feature documentation of the developed software
    • Performed data masking by encrypting Protected Health Information(PHI) in SQL Database using AES_256 algorithm
    • Worked on specimen transaction databases and developed billing algorithm which may lead to revenue growth of about $10k
    • Performed database migration, integration and indexing from legacy third party database to in-house SQL database

    Skills : Data Analysis, Data Management, SQL, Microstrategy

  • Jan 2017
    -
    May 2017

    Northeastern University

    Reserach Assistant

    • Assisted Republic of Moldova and United Nations Development Program (UNDP) in population estimation through household energy consumption data
    • Examined spatial data using ArcGIS(Global Information System) to analyze, and understand patterns of the distribution of Spatial Data, and to establish its relationship with factors like economy, terrain and geographic location
    • Performed Linear Regression, Multi-variable Regression and other advanced data statistical predictive model to derive key econometric indicators to deduce shadow economy share in state's economy
    • Performed clustering analysis to identify the similarities between growth patterns, economies of post soviet states

    Skills : R, Python, Tableau, R Libraries (rpart, ggplot, Regression)

  • Sept 2015
    -
    May 2016

    Cognizant Technology Services

    Programmer Analyst

    • Worked closely with Finance and Banking business unit to gather business requirements and to prioritize tasks
    • Performed ETL to migrate data from multiple sources to designed ecommerce data warehouses using SSIS
    • Analyzed data and developed BI reports consisting of KPIs and Scorecards using Tableau to improve corporate profitability measures and comparative marketing, sales and financial analysis
    • Designed and developed database for a Web App. for the enterprise business unit
    • Researched and analyzed fields which are required for bank transactions, comprehensive data storage of the banks, current practices and compliance for improvising the design and usage
    • Created logical and physical database designs along with data structures, procedures and triggers for Hospital Management System using SQL server

    Skills : SQL, MySQL, SSIS, Talend, ETL, HTML, CSS, BootStrap

  • June 2014
    -
    July 2014

    Omne Agate

    Data Analyst Intern

    •Assisted the firm in identifying baseline power consumption, engineering based savings and energy usage
    • Applied logistic regression to analyze and predict household energy usage (over 6000 household units) in Indore
    • Conducted data preparation, and outlier detection using MS SQL server; built the model using R

    Skills : R, SQL, Regression, Clustering

Education

  • 2016
    -
    2018

    Northeastern University

    Master Degree in Information Systems

    The coursework has a blend of technical and management subjects that helps me in growing deeper understanding regarding Information System as a whole. With focus on data analytics, machine learning and visualization, the coursework has provided me modern-day skills to use technology to improvise a business process and leverage data in making the business better.

  • 2011
    -
    2015

    VIT University

    Bachelor Degree in Electronics and Communications

    Cources: Data Structures, C Programming

Contact

20C McgreeveyWay,
Mission Mains, 02120

negi.sh@husky.neu.edu

+1 617 372 5796

Leave me a message