Data Analyst

Sai Venkata Raghava

**************@*****.*** 605-***-****

A Data Science enthusiast with 3.5 years of academic experience in Data Analytics, Machine Learning and Big Data Technologies. Solid understanding of Statistical Models, Machine learning algorithms and mathematical concepts with 1.5 years of work experience in Data Collection, Preparation, Exploration, Model building and Evaluation and Data Visualization. Good in delivering research-based, experimenting with predictive models and explanatory analysis to discover meaningful patterns and data-driven solutions that move organizational vision forward. A lifelong learner.

EDUCATION

Master of Science in Data Analytics December 2017

Dakota State University, Madison, SD GPA:3.91

Specialization Certificate in Deep Learning, Coursera December 2017 (6 Months)

Specialization Certificate in Statistics, Duke University September 2017 (6 Months)

Specialization Certificate in Analytic Techniques for Business, Duke University April 2017 (5 Months)

Specialization Certificate in BIG DATA, University of California, San Diego August 2016 (6 Months)

Specialization Certificate in Business Analytics, University of Pennsylvania May 2016 (6 Months)

TECHNICAL SKILLS

Data Analysis tools: RStudio, iPython/Jupyter, Tableau, Apache Hadoop, SAS(BASE 9.4, E-Miner

Languages: R, SQL, Python

Big Data Eco systems: HDFS, Pig, Hive, MapReduce.

Microsoft Software: Word, Excel, Project and PowerPoint

PROFESSIONAL EXPERIENCE

Collaborative Research& Data Science Intern, Sanford Health, Sioux Falls-SD Sep 17 to Present

Data mining vast, raw, and structured datasets to find key and actionable insights and generate ideas.

Performed geographical mapping of Diabetic specialists from Sanford Health to their geographical clinical locations using maps in RStudio.

Performing Data cleansing and utilizing unsupervised Machine learning algorithm such as K-Means to cluster 800000 patients into 26 groups. Researching the differences of each cluster and analyzing the importance of each variable.

Graduate Research Assistant, Dakota State University, Madison-SD Jan 17 to May 17

Worked on the development of a tool called CONSOL, which uses content, context and social features extracted from Twitter to classify short URLs.

Worked on data preprocessing steps like exploration, missing data imputation, sampling, feature selection, dimensionality reduction, outlier detection and imputation.

Researched on the statistical significance on each feature in the detection of a malicious URL.

Implemented several supervised learning algorithms such as Ensemble Methods (Random forests), Logistic Regression, SVMs, Extreme Gradient Boosting, Decision Trees, K-nearest neighbors, Neural Networks.

Statistical Data Analyst- Remote Aug 16 to Dec 16

Assisted Dr.Sekhar Pagadala(Research Associate, University of Alberta, Canada) in statistical analysis with his drug research data. Implemented Linear Regression model targeting viral proteins. Researched on the correlation of different enzymes on viral proteins.

Business Data Analyst, ZENTEN- Remote Jan 16 to Jul 16

Analyzed different organizations from the gathered data to project the past growth and force rank those organizations from one to ten by taking necessary metrics into consideration. Performed statistical analysis using R, Excel and Matlab.

Generated data summary tables, graphical representation, and model result reports in standardized formats based on requirements. Produced visuals/dashboards to convey the story inside the Data.

Contact this candidate