*** * **** ******, *** ***, AISHWARYA +317-***-****

INDIANAPOLIS, IN, 46202 KARPURAPU ac5kyt@r.postjobfree.com https://www.linkedin.com/in/aishwarya-karpurapu/

2+ years of data science domain experience through professional work and research. Specialties in Machine Learning, Statistics, and Big Data Analytics

PROFESSIONAL EXPERIENCE

Data Analyst (July 2015 – May 2016)

Keystone Data Systems Pvt Ltd

• Assigned to support Sr. Data Analysts in formulating and developing data driven applications to deliver robust software solutions and to enhance customer satisfaction.

• Designed a process flow for product development cycle to facilitate executive level people in assigning labor, development time and testing time to current and prospective projects.

• Performed daily data analytics task using python and generated reports with tableau for drawing quick insights. Research Intern (May 2015 – June 2015)

Defense Research Department Organization (DRDO)

● Developed and orchestrated a mechanism for collecting sensory data from the missile fins, which facilitates scientists for calculation of different metrics like speed, drift, and directions

● Demonstrated the data results to the scientists at the E and F level (top tier scientists) and won appreciation EDUCATION

INDIANA UNIVERSITY PURDUE UNIVERSITY INDIANAPOLIS (IUPUI) (August 2016 – May 2018) Master’s in Computer and Information Sciences (Data Science concentration) (GPA: 3.4/4.0) Course Work: Data Mining, Cloud Computing for Data Science, Data Visualization, Big Data Analytics, Big Data Management PROJECTS

Recruit restaurant visitor forecasting (Kaggle 2018)

• As a team (team leader) competed in predicting the no. of visitors for recruit holding restaurant.

• Used model stacking technique which include random forest, Xgboost and linear regression techniques for better Rmse

• Resulted Rmse: 5.632, Stacked model weights: 0.25, 0.45, 0.3 Churn prediction using Model Comparison

● Did churn prediction using Random Forest, Adaboost Classifier, and Gaussian Naïve Bayes

● Best model comparisons depending on testing accuracy

Random Forest: 0.95, Adaboost Classifier: 0.87, Guassian Naïve Bayes: 0.86

● Tools and Technologies used: Jupyter Notebook, Python (Scikit-learn, Matplotlib, numpy, pandas) A Mechanized Framework for Data Analysis and Visualization

● Developed a generalized process flow for analyzing and visualizing the data, which can be applicable to most sectors

● Case Study Yelp Dataset, Tail-end distributing of reviews for restaurant metrics. Identified less biased restaurants and Visualized their average potential scores

● Tools and Technologies used Cloud services for storing and analyzing data, Spark, SQL, Python, and Tableau SKILLS

Machine Learning: Classification, Regression, Clustering, Recommendation Systems Statistical Methods: Descriptive Statistics, Inferential Statistics Programming: Python (scikit-learn, pandas, numpy), R, PIG, C, C++, Core Java, Java Script, SQL, HTML, CSS, PHP. Data Tools: Spark, Hadoop, Jupyter Notebook, Anaconda, AWS, Matlab, NetBeans, Eclipse Databases: MySQL, NoSQL (MongoDB)

Data Visualization: Tableau, Plotly, Matplotlib, Data Driven Documents(D3) Others: Good knowledge in Computer Networks, Operating Systems, Database, Software Engineering CERTIFICATION

Machine Learning A-Z: Hands on Python & R in Data Science (Udemy)