Shravya Katukuri Email & Phone Number

Littleton, Co, Us

Englewood, Co, Us

Englewood, Co, Us

Brooklyn, New York, Us

Environments:Python 3.6, MySQL 8.x, Tableau 2019.3, Pycharm, Jupyter Notebook, Google Analytics, Machine Learning algorithms (XGBoost, K nearest neighbours), Git, GitHub.• Sourced historical and forecast weather data from an external API called “Openweathermap” by retrieving the relevant attributes and stored it in Hive tables.• Processed the data using transformations in Scala 2.12.x like map, flatMap, filter, reduceByKey and groupByKey and stored the data in an AWS S3 datalake.• Developed baseline code in Python 3.6 to incorporate that “weather” attribute into the existing XGBoost Machine Learning model that improved accuracy of energy usage predictions by 10%.• Collaborated with the development and analytics teams to create personalized recommendations for the customer based on their usage history by collecting and storing energy data from the meters in a MySQL database, applying the user-based collaborative filtering (K nearest neighbours) technique using a combination of Rating Scale approach and Pearson’s Correlation and generating recommendations in Spark MLLib.

Dublin 2, Ie

Environments:PySpark 2, Hive 2.3.6, Sqoop, AWS EMR, Tableau 2019.3, Git, JIRA, Linux, Kafka 2.4.x, MapReduce, Spark 2.x.Responsibilities:• Worked on a 3 node Spark cluster using AWS EMR with PySpark in for creating RDDs from text files containing financial transactions data and performed Transformations and Actions using Core Spark APIs to generate aggregate data metrics. • Loaded data from and saved to various file formats like text/avro/parquet/sequence files in Hive for different requirements along with different compression formats like gzip and Snappy.• Exported data from Hive into a MySQL database using Sqoop for analysis and visualization purposes.• Developed an interactive finance dashboard in Tableau 2019.3 using the filtered dataset that gives an overview of cash flows, accounts receivable and effect of different risks. Used dashboard actions, calculated fields, parameters, table calculations, advanced functions like LOD Expressions, R integration and context filters.• Utilized Spark performance tuning techniques such as persist and cache methods, broadcast variable, accumulators, data serialization, etc. to boost performance.

Dublin 2, Ie

Environments:Python 3.6, MySQL 8.x, Microsoft SQL Server 2019, Windows PowerShell, Robotic Process Automation, Git, JIRA.Responsibilities:• Analysed and interpreted daily transaction data using Python 3.6 for insights on suggesting new fare changes, introducing new buses/streetcars in routes heavily used by public, etc.• Extracted job reports, daily taps, transactions and loads of different subsystems from relational databases like ODS, DAX, RemoteListDB and DWH using MySQL 8.x.• Used Microsoft SQL Server’s BI tools like SSAS, SSIS and SSRS for analysing data, integrating the right data for effective analysis, and reporting them to the client in the prescribed format.• Used Windows PowerShell and Accenture’s customized version of Robotic Process Automation (RPA) to automate daily manual reports of the Operations teams resulting in higher bandwidth for critical tasks.• Prepared Test Scenarios and Test Cases according to the functionalities for performing manual testing, reviewed the test plan with leads to ensure coverage and identify risks and conducted Peer Review of the test cases written for functionalities.• Performed Test Execution, Test Results, defects reporting, Retesting and Regression testing and reported weekly status reports to the project team and managers.• Worked in an Agile environment while meeting requirements and used Git and JIRA for version control and project tracking purposes.• Prioritized, scheduled and completed testing tasks effectively whenever required for multiple applications with overlapping schedules.

Master Of Science - Ms, Business Analytics And Information Systems

Bachelor’S Degree, Mechanical Engineering