Bhavani Prasad Rao Ejanthkar
Data Scientist Data Engineer Data Analyst
adg1j2@r.postjobfree.com
Indianapolis, IN
linkedin.com/in/bhavaniprasad73
SKILLS
Programming Languages: Python, R, SQL, Tableau, Power BI, Excel Machine Learning/Data Science: Predictive Modeling, Regression, Clustering, Classification, Anomaly Detection Libraries: Tidyverse, NumPy, Pandas, SciPy, Scikit-Learn, Matplotlib, Seaborn, Bokeh Techniques: ETL, Data Cleaning/Quality/Extraction/Visualizations, Supervised/Unsupervised Learning Cloud Platforms: AWS, Azure, Databricks
Distributed Computing: Hadoop, Spark, PySpark, Spark SQL, Pig, EMR Leadership: Cross-functional teammate capable of communicating business objectives into actionable insight EXPERIENCE
Data Scientist Consultant 01/2020 – 07/2020
Solware IT Technologies (DXC Technology) Tysons, VA
Project Requirement: To build the data architecture for the ETL pipeline that automates key business decisions
Created MySQL database that pulls the data from legacy systems
Developed connection between MySQL and Python for cleaning and data quality check
Built a scalable ETL pipeline that automated the dashboard and reports in Power BI and Excel
Built a Proof of Concept predictive models to estimate the projected revenue for next quarter and year using Linear Regression model
Communicated actionable insights from data for deriving strategy and helped leadership for making informed decisions
Co-founder 01/2019 – Present
Zenext LLC Indianapolis, IN
Mission: To build AI driven Voice Assistant Device for Law Enforcement Officers in the US to make public communities safer
Collaborated and performed User-Centered Research with Carmel PD, NYPD, CMUPD, and Chicago PD to collect pain points and challenges the Police Officers are facing in an operational environment
Partnered with Carmel Police Department to test the solution in real-time
Received total funds of $112k support from NIST to advance in developing the solution further
Developing best-in-class product through cutting-edge technology for advancing public safety communications to help emergency responders save lives Database Developer and Data Analyst 12/2017 – 12/2018 IU School of Medicine Indianapolis, IN
Project Requirement: To build a database for nursing centers web application
Designed & developed the database to store, retrieve, and update data
Performed EDA on data by integrating the database with Python
Actively collaborated with team and medical professionals to align the project with their needs
The prototype won grant money of $30,000
Business Data Analyst 01/2015 – 12/2016
ProGen Business Solutions Hyderabad, India
Project Requirement: To provide actionable insights from the customer sales transactions data
Created an ETL data pipeline that pulls data from the database into Python for downstream analysis
Performed EDA to identify patterns in the customer sales data
Prepared financial and business sales revenue report using Tableau dashboards
Provided KPIs for improving the sales revenue & actionable insights for making key business decisions EDUCATION
MS, Computer Science, Purdue University, Indiana, USA 12/2018 BS, Computer Science, JNTU, Hyderabad, India 06/2015 PROJECTS
Bank Marketing Campaign Prediction Using PySpark and MLlib in Databricks
Goal: To build the end-to-end data science pipeline for predicting whether the client subscribe to a term deposit or not?
Extracted, transformed, and loaded data into an DBFS table
Created Spark Cluster and performed EDA and Feature Engineering in Python
Implemented Logistic Regression, Random Forest, Decision Tree, and XGBoost model for predicting the patients’ heart disease
Achieved optimized accuracy score of 90.8% with an XGBoost model after performing hyperparameter tuning
Heart Disease Prediction Using Spark in Databricks
Goal: To build the end-to-end data science pipeline for predicting the heart disease using Spark SQL and PySpark in Databricks
Extracted, transformed, and loaded data into an DBFS table
Created Cluster and performed Data Cleaning, Data Quality check, and EDA in Jupyter Notebook
Implemented Decision Tree model for predicting the patients’ heart disease
Achieved optimized accuracy score of 98.3% with improved time and space complexity
Built scalable workflow that is 20x faster than Hadoop for large scale data processing Airplane Data Analysis Using Apache Pig
Goal: To find store, process, and build the ETL Pipeline for analyzing 1 million rows of data in AWS using NoSQL database (Apache Pig)
Extracted, transformed, loaded data in S3 bucket
Ran the MapReduce job in the EMR Cluster and computed with the EC2 instance
Performed Analysis on 1 million records of airplane traffic data
Achieved insightful information with high efficiency and less time Illinois 101st General Assembly Prediction
Goal: To predict whether the bill is Public Act or not?
Created an end-to-end data science pipeline
Extracted data from website through web-scraping in Python
Performed EDA, Statistical Analysis, and Data Visualization
Implemented Oversampling, Undersampling, and SMOTE on the Imbalanced Classes
Performed classification using Logistic Regression, Random Forest, XGBoost, and Decision Tree
Achieved the best Recall score of 1.0 with Logistic Regression Apple App Store Data Analysis
Goal: To find top 300 apps that had best rank growth over the past 365 days
Cleaned data and performed EDA and Feature Engineering in Python
Performed Statistical Analysis and Data Visualization to communicate the results
Provided actionable insights and KPIs to make key business decisions