Data Analyst Python

PRIYANKA KANDREGULA Authorized to work in the US

********.***********@*****.*** 313-***-**** Dearborn, MI-48126 www.linkedin.com/in/priyankakandregula

Salesforce: https://trailhead.salesforce.com/me/pkandergula GitHub: https://github.com/kssvsp

Looking for internships and full-time opportunities where I can use my knowledge for the benefit of the organization and to gain new skills. Data Science graduate with 2 years of experience in Data Visualization, Database Systems, Develop Dashboards, Data Mining, Data Analysis, Statistical Analysis. Proficient with Tableau, MySQL, Python, R, C, C++, ETL, Excel.

EDUCATION

Master of Science in Data Science - University of Michigan-Dearborn GPA-3.8 Expected Dec’20

Bachelor’s in Information Technology - JNTU College of Engineering, India GPA-3.8 Sep’14 -May’18

ACADEMIC PROJECTS

Use of Predictive Modelling in Healthcare: Tools: Python, Tableau, Excel Sept’19-Dec’19

Implemented Logistic Regression on Breast Cancer Stage prediction, attained an accuracy of 90.15% and implemented Linear Regression on Cost Analysis for Hospital Readmission, obtained an RMSE value of 6724.911.

Yelp Review Analysis: Tools: Python, Excel, R, Tableau Sept’19-Dec’19

Implemented Ordinary Least Squares, Linear Regression, Principal Component Analysis and Linear Discriminant Analysis on the Yelp dataset and attainted MSE values for OLS and Linear as 89.7 and 89%. Accuracy for PCA, LDA as 76 and 42%.

Data Analysis and Recommendation Systems: Tools: Python, Excel Sept’19-Dec’19

Used Simple, Content-Based and Collaborative Filtering Algorithms to make recommendation of movies to users- Big Data.

Natural Language Processing Project: Tools: Python, Excel, Word (Dictionary) Jan’19-Apr’19

Implemented Language Models (splitting words & spelling correction) to improve Optical Character Recognition from printed text images, attained accuracy of the printed images by 71%. Also worked on Sentence Boundary Detection.

Netflix Show Tracker: Tools: Python, MySQL, HTML, CSS Jan’19-Apr’19

Developed a Netflix Show Tracker website with user interactive features focused on database storage and retrieval.

PROFESSIONAL EXPERIENCE

Graduate Research Assistant-University of Michigan-Dearborn, Michigan Oct’19-Present

-Working on Bioconductor package for integrative analysis with GDC. Performing analysis on the PAN cancer data in R.

-Searching, Downloading and Visualizing mutation files, TCGA data, GDC databases in Python.

Business Analyst Intern - TecFinics Technology Solutions - Hyderabad, India May’18-Dec’18

-Devised logistic regression model in Python to assess the chance that customer will respond to direct marketing mails.

-Gathered data using SQL, interpreted data to increase sales, translated the findings into Tableau reports and presented.

Data Analyst Intern - Salesforce - Hyderabad, India Jan’18-May’18

-Worked on Salesforce CRM tool, analyzed requirements to create reports and dashboards for E-Commerce clients.

-Visualized the data with Lightening Dashboard Builder and extended reporting strategy with AppExchange.

Data Analyst Intern - Deloitte - Hyderabad, India Sept’17-Dec’17

-Developed and tested extraction, transformation, and load (ETL) processes using IBM DataStage.

-Analyzed and executed the test cases for various phases of testing – unit, integration, regression, system, and user.

Data Analyst Intern - Innovative Software Solutions - Hyderabad, India May’17-Sept’17

-Performed Statistical modeling on gas-turbine data. Created and updated databases by SQL, accessed data from Jupyter.

- Developed ad-hoc and customized reports using SQL Server Reporting Services (SSRS).

Graduate Teaching Assistant - University of Michigan - Dearborn, Michigan Jan’20-Present

-Performing Descriptive Statistical Analysis and Data Analysis on Excel for DS-302 Business Statistics assignments, projects.

Graduate & Undergraduate Tutor - University of Michigan - Dearborn, Michigan Jan’19-Present

-Tutor for Probability Statistic courses and in addition give assistance on other Computer and Information Science Courses.

TECHNICAL SKILLS

Programming Languages: Python (OOPS, Pandas, NumPy, NLTK, Scikit-learn, TensorFlow, Matplotlib, Seaborn, SciPy, Statsmodels, Plotly, Keras, ggplot2), R, ETL, MapReduce – Hadoop, HDFS, C, C++, MySQL, HTML, XML, CSS, Java, JavaScript.

Machine Learning: Logistic/Linear Regression, Classification, Random Forest, Naïve Bayes, Time series, Clustering.

Tools: Tableau, ETL, Eclipse, Cloudera, MS Excel, MS Office, Anaconda, Jupyter, PyCharm, RStudio, Weka.

Contact this candidate