Venkata Prudhvi Raj Indana (Data Scientist Data Analyst)

Redmond 98007 (WASHINGTON) 812-***-**** ac854g@r.postjobfree.com https://github.com/prudhv16 SUMMARY

Data Science Professional with 5 of experience working with cross-functional teams for deriving impactful business solutions. Highly proficient in Python, data science libraries. Have Deep mathematical understanding of machine learning and deep learning models. Best practices in software development with Agile/Scrum methodology, code reviews. EDUCATION

Master of Science, Data Science - Indiana University - Bloomington May 2017 Courses: Statistical Inference, Design and Algorithm Analysis, Data Mining, Exploratory Data Analysis, Artificial Intelligence, Applied Machine Learning, Information Retrieval (Search), Machine Learning, Multivariate Data Analysis, Machine Learning in Bioinformatics. Bachelor of Technology, Electronics and Communication - Gitam University, Visakhapatnam. May 2012 WORK EXPERIENCE

Data Science Consultant, Microsoft (Affine Analytics), WA May 2018 - present

• Explored Tenant usage data from different perspectives (Free/Paid O365 Consumers by SKU, Tenure, Status). Performed extensive data exploration generating Tenant level, page level features over 1TB/day JSLL click stream data in cosmos.

• Responsible for Lead scoring analyst evaluating Deep learning model, debugging issues after deployment.

• Performed time-based cohort analysis reporting new customer Acquisition by seats/ number of products in multiple channels.

• Managed 2 offshore team members tasks and deliverables. Maintain and improve engagement models within the Lifecycle framework. Data Science Consultant, Expedia (Affine Analytics), WA Dec 2017 - May 2018

• Developed a scalable workflow to segment customers and allocate travel destinations/ hotels for Expedia customers based on email templet designed by marketing managers, sending emails to 23Mil users (full base campaign) in US.

• Established relationships and maintained communication with 3 client teams and 5 offshore team members, managing project delivery deadlines.

Software Developer Intern, Bloom Insurance agency, IN Jun 2017 - Dec 2017

• Developed new features in an Enterprise facing product line in technologies such as C#, MVC, MVVM, ASP.NET, Xamarin Studio. Wrote software documentation, unit test, and QA test scripts. Data Analyst Intern, Arborgold Software, IN May 2016 - Aug 2016

• Extract, transform and analyze data from SQL server and identify trends in data by visualization.

• Create a new reporting tool (Owners app Dashboard) having various Visualizations/reports plotted on a web interface in MVC C#, JavaScript, SQL Server, server and Kendo UI.

Software Developer / Data Analyst, United Health Group, India Dec 2014 - Aug 2015

• Formulated problem and build a classification model to predict customer payment issues tickets.

• Segmented user data utilizing K-means clustering and analyzed customer’s behaviors based on demographic data, regions, and illness to find most frequent illness per region and recommended preventive measures for the same.

• Collected unstructured historical claim data from archives, new claim data from multiple data sources, preprocessed and cleaned data to the same format.

• Applied preprocessing techniques, feature transformation, missing value treatment and generated a logistic regression model with grid search and 10-fold cross-validation to tune model parameters. Engineered an ensemble of Naive Bayes, SVM, and Decision Tree classifier to classify emails with 93.7% test accuracy. Software Developer / Data Analyst, Computer Science Corporation, India Jul 2012 - Dec 2014

• Build data pipelines importing data from local server to IBM Z/OS, validates input data and rejects/ recycles/processes payments for claims in data by stored procedures written in COBOL.

• Collected claim data from existing claims for both customers and insurers platform and consolidated data analyzed the same for process control failure as well as to propose early fraud indications.

• Visualized fraud data grouping by fraud and created a histogram showing top 20 fraud.

• Developed a classification model to predict the probability of a new Medicare claim being rejected using claim data. Achieved an accuracy of 86% after model parameter tuning and 10-fold cross-validation. ACADEMIC PROJECTS

• Kaggle House Price Prediction: Performed extensive data exploration, engineered and transformed useful features based on adjusted R2 values. Engineered a Stacking Ensemble for predicting house prices using Gradient Boosting with Huber loss, Lasso, Ridge, and Elastic Net Regression and Random Forest Regressor. Ranked top 10% in Kaggle.

• Implementation of Bayesian spam filter using bag of words algorithm obtaining an accuracy of 87%. Spam filter code is extended to classify genera of a 20 Topic in fully supervised (72%), semi-supervised (47%), unsupervised (6%). TECHNICAL SKILLS

Programming Languages: Python, R, C#, SQL, Javascript, Java, Hadoop, pyspark. Tools: Tableau, R-Studio, Jupyter, PIG, JIRA, Hive, WEKA, Git, Github, Markdown, Excel, Redshift, Confluence, Remedy, VSTS. Statistical Methods and Mathematics: - Hypothesis testing, Probability, Calculus, Linear Algebra. Data Science Libraries: Tensor-flow, Keras, sci-kit-learn, pandas, numpy, matplotlib, ggplot2, pyspark. ML Tools: Regression, Classification, Dimensionality Reduction, Ensembles, Deep Learning, Time Series, Big Data.