Data Analysis

ANUSHA YERUVA

*** ***** ****** ****** *** Jose, California 95112 650-***-**** ************@*****.***

SUMMARY

An analytical and meticulous data scientist with expertise in R, Neural Networks and Business Intelligence tools like Tableau adept at assisting organizations leverage strengths through data insights and delivering value to the organization. Driven to achieve results and exceed expectations to ensure an enterprise’s sustained success.

TECHNICAL SKILLS

R Programming

Exploratory Data Analysis

PL/SQL

MS Word

Statistical Analysis

HIVE

ggplot2

MS PowerPoint

Data Modeling

Unix Shell Scripting

Advanced MS Excel

MS Visio

Tableau 10

SQL

R Studio

HDFS File Systems

Data Cleaning

Neural Networks

Data Cleansing

Data Sampling

PROJECT WORK

Build a predictive model on customer purchasing habits using logistic regression to find out their inclination of purchasing products in multi commerce channel, so that retail businesses can position the product availability at the highly preferred channels and ensure advertising resources are strategically spent.

oLoad data into R from CSV file and identified missing data structure for all the variables.

oThen performed Exploratory data analysis on a sample data – Descriptive statistics, cleaning in replacing the missing values and outliers with average value.

oUsing Hypothesis testing, identified the variables of more significance, to build more accurate model.

oBy applying statistical technique logistic regression got the best model in multiple iterations.

oThen validated the model by using ROC curve and confusion matrix.

Performed Market Basket analysis on historic transaction data of a retail store to find out what products go together in a basket, so that businesses can strategically come up with promotions and association of products in the store.

oFormed association rules on groceries dataset from arules package in R.

oPerformed multiple iterations by changing the values of confidence and support.

oInspected the top 20 rules to create association rules.

On super store data using tableau, able to figure out the factors that are affecting the performance of stores in certain states, so that businesses can focus on solutions to improve the performance and visually illustrated by building Dashboards.

oConnected superstore data source to tableau, build visualization for all the stores and their corresponding profits then, created a set for states that are in negative profits and compared them with the rest of the states.

oThen analyzed their performance in different quarters by drilling down to each category of products.

oThen created visualization showing the factors that are affecting the stores performance.

CERTIFICATIONS

Certified Business Analyst in R

EDUCATION

Jawaharlal Nehru Technological University, Hyderabad.

B. Tech., Electronics and Communication

Contact this candidate