Shruti Gupta

908-***-**** ● College Park, MD, **740 ● adbb5h@r.postjobfree.com ● www.linkedin.com/in/shrutiln/ EDUCATION

University of Maryland, Robert H. Smith School of Business College Park, MD, USA Master of Science, Information Systems, GPA 3.65 December 2019 Relevant Coursework: Machine Learning, Data Mining and Predictive Analysis, Database Management, Business Process Analysis, Data Models, Data Visualization, Strategic and Transformational IT, Big Data and Artificial Intelligence Jaypee Institute of Information Technology Noida, Uttar Pradesh, India Bachelor of Technology, Information Technology June 2015 TECHNICAL SKILLS

● Tools and Language: SQL, Python, PySpark, R, PL/SQL, Postgres, Git, Superset, Confluence, MS Office Suite, Advanced Excel, Pentaho, Databricks, HTML, CSS, Lucidchart

● Packages/Libraries: Python (pandas, numpy, scikit-learn, matplotlib, keras, seaborn, smtplib, urllib, plotly)

● Business Intelligence: Tableau, Excel Solver, Pivot Table, VLOOKUP, SAS, AWS, S3, Hadoop, Spark, Sqoop, Pig, Hive

● Certifications: Tableau Desktop Specialist, Google Analytics & AdWords, Data Scientist track with Python WORK EXPERIENCE

Morten Beyer & Agnew Arlington, VA, USA

Data Analyst Intern May 2019 – Aug 2019

● Implemented successful conversion of legacy Pentaho Kettle to develop a more flexible and advanced ETL pipeline using python by puling data from various sources, optimized and automated the entire process

● Created views and functions in plpython3 to set up a RESTful API on postgREST to compute inflation adjusted aircraft values and historical fleet data of over 44,000 aircraft

● Provided meticulous version control of API codebase and documentation on a GitHub repository, performed source audit, designed and developed dashboards to drive better client insights Office of Career Services, University of Maryland College Park, MD, USA Graduate Assistant, Business Intelligence July 2018 – Dec 2019

● Improved lead to conversion ratio by 30% by providing insights for targeted employer outreach campaign

● Integrated data of past five years of UMD Alumni to build an interactive interface using complex SQL in the backend to analyze employment trends in Smith Business school Running Start Washington DC, USA

Consultant Jan 2019 – August 2019

● Analyzed the OCS official website ‘inTERPretations’, proposed insights based on Google Analytics to increase viewership and engagement for successful conversions

● Improved website traffic through data analysis using Google Analytics by 60% Ernst & Young LLP Gurgaon, Haryana, India

Risk Analyst Consultant, Performance Improvement July 2015 –July 2018

● Performed predictive modelling for a Telecom giant using Logistic Regression model, predicted churn rate of customers with accuracy of 74.2%, further increased it to 78.6% using SVM algorithm

● Optimized the existing reporting process by developing complex SQL queries and python scripts to integrate data from multiple sources leading to increased productivity

● Automated metrics to track weekly status and detect data anomalies of multiple BI dashboards through Tableau, reduced manual intervention/ad-hoc requests by 40%

● Managed a team that analyzed change management, access management and backup logs for SOX 404 Compliance to formulate roadmap for data security

● Led coordination role for clients including planning, briefing team on client’s IT environment and industry IT trends, coaching and mentoring team, felicitated with Extra Miler’ award for exemplary performance PROJECTS

Python, Naïve Bayes, Ensemble Methods: Predictive Modelling using NumPy, Pandas, Scikit, Datetime

● Led data joining, cleansing and preprocessing of 6 million data points of crime data of Chicago, performed Lasso feature selection applied Logistic Regression, Naïve Bayes and Boosting to achieve classification accuracy of 86.48% Tableau: Analyzed Superstore dataset using calculated fields, visual grouping, sets, parameters link

● Examined relationship between orders and sales containing orders from superstore data of 10000 records, formulated metrics like shipping performance, Year over year sales, data aggregation to analyze data Big Data Analytics: Regression Predictive Modelling using PySpark and MLlib

● Built and managed multi node Spark cluster using Databricks, classified results of direct marketing campaign to identify customer lifetime value by implementing Logistic Regression and Decision Tree classifier using MLlib