Data Engineer

Raghava Prasad Sridar

*************@*****.*** +1-469-***-**** Dallas, TX linkedin.com/in/raghava-prasad-s github.com/RaghavaPrasad

EDUCATION

Master of Science, Business Analytics (Data Science Specialization) Jan 2020 - Dec 2021 The University of Texas at Dallas

Bachelor of Science, Computer Science and Engineering Aug 2013 - May 2017 SCSVMV University, India

SKILLS

Languages: SQL, Python, R, Stata, SAS, C/C++

Machine Learning Libraries: Numpy, Pandas, MatplotLib, Seaborn, Scikit-Learn, Keras, TensorFlow Tools/Technologies: MongoDB, AWS, GCP, Azure, Git, Docker, Tableau EXPERIENCE

Programmer Analyst, Cognizant Technology Solutions Nov 2017 - Aug 2019

• Built resilient ETL data pipelines for batch processing using Pentaho Data Integration, impacting 20+ internal appli- cations and its 10000+ users.

• Scripted SQL Queries and Stored Procedures for efficient data retrieval, achieving 1.5X faster optimized queries.

• Built a Risk Prediction system with Microsoft Azure and Python that identified projects ahead of falling into the Risk category, directly saving costs.

Solution Engineer Intern, Nokia Solutions and Networks Sep 2017 - Nov 2017

• Researched and Proposed potential applications of Mixed reality as a part of Nokia Innovation Team using Microsoft Holo-Lens that can be applied in the industry for immersive learning experience. PROJECTS

Time Series Analysis (STATA, Tableau)

• Time Series Analysis on Traffic Deaths across the states of US, researching on how drinking laws affect traffic deaths using STATA and suggested stricter laws that could reduce traffic deaths significantly. TV, halftime shows, and the Big Game (Python, Tableau)

• Cleansed the data, performed extensive Data Wrangling and Exploratory Data Analysis ( EDA, Numpy, Pandas).

• Identified hidden trends, answered important analysis questions including predicting next season’s winner and most prolific musicians.

Object Detection System with Amazon SageMaker (AWS, Sagemaker)

• Built an end-to-end Machine Learning model with Labelled Images of bees, tuned hyperparameters to achieve accurate object detection.

Twitter Sentiment Analysis (R, Weka)

• Performed Sentiment Analysis of Twitter feeds to gauge the reaction of fans on cricket matches in the Indian Premier League (a leading cricket tournament).

Predicting Current Market Values for Houses (Python, Tableau, Scikit-Learn)

• Built an Supervised Machine Learning model to predict house prices based on real housing data (zillow.com) for multiple counties across the US.

• Aggregated data through Web APIs, performed data wrangling and data cleaning for more than a million records.

• Implemented Feature Engine Pipelines, used GridSearch to find best hyperparameters and best performing algorithms using Ensemble learning.

Seattle Airbnb Data (MySQL)

• Designed E-R Diagrams, Developed the database from scratch and created tables at 3NF from raw data.

• Written SQL Scripts and reported important insights to better understand the customer satisfaction on the current property prices and amenities.

COURSEWORK

• Applied Machine Learning, Supervised and Unsupervised Learning (Linear models, Logistic regression, SVM, Decision Trees, Random Forests, Ensemble Methods, Neural Nets, PCA), Deep Learning (PyTorch, Keras), Imbalanced Data, Predictive Analytics, Statistical Analysis, Hypothesis Testing, Significance Tests, Bass Models, Heteroskedasticity, Con- joint Analysis, Survival Analysis, Time Series Analysis ADDITIONAL INFORMATION

• Student Ambassador, Graduate Deans Council Member, UTD Data Science Club Data Science Author, Medium.com

Contact this candidate