Post Job Free

Resume

Sign in

Data Analyst, Data Science, SQL, Tableau, Power BI, ML

Location:
Dallas, TX
Posted:
February 23, 2020

Contact this candidate

Resume:

Meghana Gangarapu

Dallas, TX* 469-***-**** * adbxxg@r.postjobfree.com * https://www.linkedin.com/in/meghana-gangarapu/ EDUCATION

The University of Texas at Dallas Dallas, Texas

M.S, Business Analytics; May 2020

Coursework: Statistics, Probability, R, Python, DBMS, Machine Learning, Predictive Analytics, SAS, Big Data

Indian Institute of Information Technology India

B.Tech in Electronics & Communication Engineering; May 2016 SKILLS

Languages: R, Python (Numpy, Pandas, Scikit-Learn) C#, SAS, MATLAB BI tools: Tableau, Power BI, Alteryx, Excel, Google Analytics Data Warehouse Tools: Microsoft SQL Server, Oracle SQL Developer, MySQL, MongoDB Statistics & Machine Learning: Regression, Statistical modeling, Hypothesis Testing, Time Series Analysis, Clustering, Decision Trees, KNN, Ensemble Methods, Random Forests, Support Vector Machines, Gradient Boosting, XGB, Neural Networks, TensorFlow, Principle components, Feature engineering, Hyper Parameter tunings Certification: Tableau, Google Analytics

EXPERIENCE

IntelliCentrics Data Science Intern June 2019

• Built Interactive visualizations to allow users to ask & answer questions through guided analytics to support knowledge acquisition and decision making.

• Performed Exploratory data analysis to extract insights to understand various features affecting the user churn.

• Built ensemble models in python to predict users churning from subscription.

• Performed hyper-parameter optimization and improved the predictive capability of a churn prediction model by 8%.

• Used aggregate function to build complex SQL queries.

• Work in a cross functional environment with various business groups, IT and end users to identify, document, and communicate business processes.

Infosys Limited Data Analyst May 2016 –June 2018 D-Mart Sales Analysis: To analyze the effect of various factors affecting the sales of 2500 products across 25 stores in different cities.

• Developed models and performed Exploratory data analysis to extract insights to understand various features affecting the sales of client.

• Used dashboards and data visualization for insights, and to understand the top 14 features affecting the sales at various points in the funnel.

• Conducted data cleaning to understand deviations in the data to and addressed missing values and encoded categorical variables and discarded outliers etc.

• Performed feature engineering and feature selection to find important features, performed PCA to reduce the dimensions for model training.

• Built K-means clustering model to understand the market segmentation and customer purchase characteristics and improved the performance of the model by 14%.

eBay Inc Data Analyst Intern May 2015 – Dec 2015 Applied data and analytical skills to understand Global Customer Experience Strategic Analytics

• Collaborated with the team of Data Scientists and executed cohort analysis to understand customer behavior and identity the opportunities to improve the products.

• Built models to project key business metrics like conversion rate, Customer Engagement - and developed KPIs to measure initiative performance.

• Designed interactive dashboards, identified key trends, understand different groups and behavior of customers.

• Increased Engagement by 2.5%, conversion rate by 7% using recommendations to enhance application which were backed up with the data.

PROJECTS

Housing Prices Analysis & Prediction: Kaggle

Performed data cleaning and Exploratory Data Analysis to find patterns and useful relationships.

Performed feature engineering, Dimensionality reduction and encoded categorical variable using one hot encoding.

Predicted housing prices using Regression, Random Forests, and ensemble methods of stacking and boosting. Titanic Survival Analysis: Kaggle

Preprocessed the data by handling missing value, performed data wrangling and EDA on missing data.

Performed analysis and predicted survival of the passengers using logistic regression & Random Forest. Spam Email Classifier:

Built a Naive Bayes model using pandas and scikit-learn to predict spam emails by using proportions of spam trigger words as features and achieved 94.2% accuracy

Customer Churn Data Analysis:

Performed Survival Analysis to understand the differences in customer lifetime between cohorts.

Performed cohort analysis, user retention and user churn analysis to find patterns and relevant numbers to calculate metrics.

Attempted to find similarities in patterns of those users who have churned or retained by clustering them using K- means.

Implemented logistic regression model and Lasso Model to find out the likelihood of customers to stop subscription. AWARDS

Deans Excellence Scholarship (JSOM Graduate Scholarship) . August 2018

“Best Team” - For valuable contribution and outstanding performance from Infosys’s Source Rewards and Recognition. January 2018



Contact this candidate