Tanmayi Vetukuri

Studied at The University of Texas at Dalla
Living in United States

Experience
Big Data Engineer Intern - Allegis Group, Hanover, MD
May 2019 - August 2019
• Developed shell scripts in Linux to reduce backup time of Hive tables from 1 hour to under 30 minutes
• Collaborated with Data engineering team to automate data migration between clusters resulting 40% decrease in migration time
• Determined KPIs to monitor workload, job performance and capacity planning of servers on Cloudera Manager
• Modified performance tuning parameters in Hadoop cluster that helped increase performance of nodes by 30%
• Designed interactive Tableau dashboards to monitor server activity, data flow, usage statistics of nodes to senior management that improved decision times by 50%

Data Analyst - Alltronics Technologies
May 2017 - June 2018
• Performed analytics and data blending, clustering on 5+ million records obtained from multiple sources
• Assisted developers to build an Android application for users to determine accident-prone areas
• Employed statistical techniques to determine hot spots that can reduce accidents per year by about 50%
• Conducted detailed analysis, dashboards to identify actionable insights for client that help in decision-making to implement accident prevention measures and removal of hot spots

Assistant System Engineer - Tata Consultancy Services Limited August 2016 - February 2017
• Implemented SQL queries to standardize content from distinct databases and load into target databases enabling insurance agents to quickly respond to customer requests thereby increasing customer acquisition rate by 25%
• Analyzed 10+ test cases based on transformation rules and performed data integrity verification between source systems
• Performed ETL testing on mappings in Informatica PowerCenter that optimized process time by 40%
• Coordinated project requirements within an agile team employing tools such as Confluence and JIRA, ensuring project delivery times
Projects
Predicting Used Car Prices using Machine Learning models | Python, Tableau
• Performed data cleaning, and EDA on 250k+ records with 26 variables using NumPy, Pandas, Matplotlib
• Applied predictive models (linear, random forest, ridge) to predict price of used cars, obtaining R-square value of 63%

Real-time Twitter data analysis using Hadoop | HDFS, PIG, Hive, Sentiment analysis
• Retrieved 500k tweets from Twitter (using API) using Apache Flume to capture tweets and load into HDFS
• Analyzed data to determine 5 popular hashtags, resulted in classifying 35% positive tweets on demonetization

Predictive and Marketing Analytics | SAS
• Carried out hypothesis, t-tests and ANOVA tests on customer segments to identify the most profitable buyers
• Developed trend analysis reports using regression models to predict overall net sales with 84% accuracy

Sales Analysis for Global Bike Corporation |SAP Business Objects, MS Excel
• Performed analytical decision making on historical sales data of products across 30 countries using OLAP techniques
• Identified top 3 factors (products, regions, technology) that contribute to increase in sales by developing trend analysis reports