Krishna Gollapudi
Senior Data Analyst
Krishna Gollapudi
Senior Data Analyst
• Over 8 years of experience in design, analysis, development, and implementation of various applications using Data Engineering/ BI tools
• Experienced in Data Warehousing, Descriptive, Predictive and Prescriptive Analytics delivering greater insights into the financial drivers by analyzing the data at a granular level
• Strong hands-on experience designing Dashboards using Tableau Desktop and Server, implementing Data Analytics using Microsoft SQL Server, SAS, Data Lake, AWS tools
• Experienced in data modelling in Python and SQL. Proficient in Transforming large data sets using ETL tools like SSIS, Pentaho Data Integration and Big Data technologies like Spark and Hive
• Extensive experience in requirement gathering, creating rich visualizations using Tableau/ Power BI/ QlikView and translating business requirements into actionable insights through compelling dashboards.
• Deep understanding of Software Development Life Cycle (SDLC) as well as Agile/Scrum methodology to accelerate Software Development iteration and ability to handle multiple tasks concurrently to meet the deadlines
I am actively seeking opportunities in an organization where I can apply my academic and professional background skills.
Work Experience
-
CoStar Group – Atlanta, GA,USA.
May 2022 – PresentSenior Data Analyst
Responsibilities
• Partner across departments to identify key information gaps and plans to provide or obtain that information
• Build analyses and reporting for departments to increase efficiency and visibility across the business
• Creating datasets in SQL from existing company applications
• Writing SQL stored procedures, jobs and/or ETL scripts
• Creating dashboards for internal stakeholders to measure KPIs
• Perform predictive analysis using both newly created and existing datasets to identify process improvement opportunities and/or trends to determine effectiveness
• Perform ad hoc analyses at request of senior leadership -
BENEFITS SCIENCE TECHNOLOGIES, Boston, Massachusetts, USA.
Oct 2018 – May 2022Data Analyst
Responsibilities
• Design, Analyse, Synthesize and Develop automated Data Pipelines, Data Models ,Data ETL(Extract Transform Load) planning, delivering, and presenting healthcare/health insurance projects
• Collaborated with business users to identify key business requirements and functional specifications for data reporting processes to achieve better output that satisfies the business requirements
• Worked with Clients, Account Managers, Actuaries to design optimized healthcare insurance plans; responsible for developing data insights, optimize reports and structuring product line
• Developed Descriptive, Predictive and Prescriptive analytics reports to the stakeholders on Large Claimants, Risk Scores, Comorbidities, Clinical & Financial Analysis, Inpatient/Outpatient Analysis, High-Cost Claimants
• Worked in all phases of projects effecting data integrity, requirements gathering, documentation, technology evaluation, solution design, implementation, testing and user training
• Serve as SME to do full stack development starting from Data Management, ETL process development, database design and implementation to assist in Tableau Server administration and Data Visualization
• Helmed projects to initiate required procedures designed to overcome any setbacks starting from documenting root cause and providing analytical solution in the Data Engineering/Reporting pipeline
• Responsible for designing ETL processes using Python and Pentaho DI, developing source-to-target data mappings, data transformations, integration workflows and load data to tableau server for providing Business Intelligence Tools to clients
• Created prototypes and worked with stakeholders to gather requirements on data merging, de-duping, overseeing the design and development to improve KPI and make data-driven decisions
• Assist in identification of areas affecting data integrity and coordinated corrective actions including analyzing existing data platform to identify weaknesses and develop solutions for improvement, upgrade or replacement and test data-cleansing processes to support ongoing clients and new client implementations -
ProLytics LLC, Charlotte, North Carolina, USA
Jan 2018 - Apr 2018DATA SCIENTIST INTERN
Responsibilities
• Performed advanced statistical analysis and predictive modeling on MLB, NBA Draft data (3 years of NBA data) and NCAA college stats
• Adapted Machine Learning algorithms in predicting player’s match up analysis based on their game position, historical NBA data
• Data wrangling of MLB data and predictive analysis on the performance of each player in future matches
• Developed an LSTM RNN to project player’s expected performance in the draft over 2-3 years Technologies: Python, H2O, XGBoost, LSTM RNN, Classification Models
Technologies: Python, H2O, XGBoost, LSTM RNN, Classification Models
-
Accenture, Hyderabad, India
Mar 2016 - Dec 2016Associate Software Engineer
Responsibilities
• Contributed as an Associate Software Engineer with Global Resource Management project for client: Microsoft with Agile methodology
• Ad-hoc reporting for 2 teams by comprehensively using the SSRS tool, which included developing and sending reports to the higher management at the local and global level
• Modified the web test scripts according to the API changes and created pipelines in Azure Data Factory(ADF), SQL Jobs
• Executed constant/load tests in azure which included performance monitoring, performance test analysis, performance tuning
• Managed the identification and implementation of KPIs and metrics to ensure third party compliance with data requirements
Technologies: SQL Server Management St
-
HCL CDC, Hyderabad, India
Dec 2015 - Feb 2016SOFTWARE TRAINEE INTERN
Responsibilities
• Worked on an Internal project of HCL for Customer Query Tracking System
• Responsibilities include system design, creating E-R diagram, tables and stored procedures
Technologies: MySQL
-
Infosys Limited, Mysore, India
June 2015 - Nov 2015SYSTEMS ENGINEER TRAINEE
Responsibilities
• Trained on PYTHON, JAVA, HTML, CSS3, JavaScript
• Designed and developed an SQL Database system for an internal Business Enterprise Application Technologies: Python, Oracle SQL, Java
Education
-
University of North Carolina at Charlotte
Jan 2017 - May 2018Master of Science: Information Technology
Relevant Coursework
• Applied Databases
• Knowledge Discovery from Databases
• Business Intelligence and Analytics
• Advanced Business Analytics
• Cloud Data Storage
• Machine Learning
• Natural Language Processing
• Algorithms and Data Structures
-
Osmania University – Hyderabad, India
Aug 2011 - May 2015Bachelor of Engineering: Electronics and Communications Engineering
Relevant Coursework
• C Programming and Data Structures
• Object Oriented Programming using Java
• Database Management Systems
• Computer Networks
• Operating Systems
• Computer Architecture and Organisation
Skills
Programming
BI/Analytics tools
Big Data
PROJECTS
-
Predict Housing Prices – Kaggle competition (Supervised Machine Learning)
Techniques Used: Feature Scaling, k-fold, Gradient Boost, Grid search
Tools Used: Python, Tableau
• Performed exploratory data analysis, feature scaling, k-fold cross validation and grid search to achieve the most approximate prediction
• Achieved an accuracy of 85 percent in predicting housing prices of King county housing data using Gradient Boosting
-
Surprising Discoveries for Online Health Information (Unsupervised Machine Learning, NLP)
Techniques: Clustering, Cosine Similarity, PAM & Word Cloud
Tools Used: R,
• Developed a computational approach using R to identify “surprising” news from a news corpus related to diabetes
• Performed clustering analysis (K-Means, K-Medoid, SK-Means), PAM, cosine similarity, and word cloud operations on the diabetes text corpus
-
Hire Heroes USA Client Management (Data Analysis and Visualization)
Techniques: Exploratory Data Analysis, Predictive and Regression Analysis, Text Mining, Decision Trees, Tableau Visualization.
Tools Used: SAS, R, Excel and Tableau
• Applied Big Data and Analytics techniques to help a non-profit organization HHUSA, better understand and optimize factors that affect their client management process, staff activities and the employment opportunities offered to veterans
• Text mining was used to generate features and predictive modelling techniques were used to model the quantities of interest
-
Spatial and Time-Series Analysis of SFO Crimes (Time Series Analysis)
Techniques Used: Exploratory Data Analysis, Time-Series Analysis, Spatial Analysis, Matplotlib Visualization
Tools Used: Python, Jupyter Notebook, Scikit learn, Pandas, Numpy, ARIMA model
• Performed spatial and time series analysis for a 15 year dataset of reported incidents from SFPD
• Arained and fine-tuned an ARIMA model to forecast the number of theft incidents per month
• Explored and visualized the variation of the spatial distribution of incidents over time
-
Lending Club - Loan Status Prediction (Supervised Machine Learning)
Techniques Used: feature selection, feature extraction, classification
Tools Used: Tools Used: Python, Jupyter Notebook, Scikit-learn, Pandas, Numpy
• Performed feature selection, extraction, built classification and ensemble methods to predict borrowers who tend to default
• Applied cross validation to select best parameters of the model and obtained 91% prediction accuracy using Ensemble methods
-
An Electronic Medical Record for an Outpatient Clinic
Techniques: UML, ER Diagrams, User Authentication, Stored Procedures, Triggers, Views.
Tools Used: MySQL
• Designed and developed a complete OLTP database for an Outpatient Clinic that can efficiently store, retrieve, manipulate, and query records
• Implemented Authentication and Role based access control to all the data tables & used views and indexes for easy data access
-
Movie Recommendation Search Engine (Recommender System)
Techniques: Association Rule Mining, Cosine Similarity
Tools Used: R, Tableau, Shiny
• Prepared a collaborative filtering recommender (CFR) system for recommending movies to users based on genre
• The Similarity Calculation Method was based on Cosine Similarity and the Nearest Neighbors was set to 30
-
Twitter Text Analysis – Movie Success
Techniques: Web Scraping, Word Cloud, Sentiment Analysis.
Tools Used: Python, Tweepy API, NLTK
• Tweets crawled using the Tweepy API in Python were pre-processed to create a corpus for analysis using NLTK module
• Performed sentiment analysis & created a tag cloud of top 50 words in the tweets to understand the audience sentiments about the movie