Programming: Python, SQL, PySpark,Hive
Analysis Tools: Spark, Tableau, Power BI, AWS Cloud, MS Excel, SSAS,SSRS,Jenkins,ETL,Azure,CI/CD
Databases: PostgreSQL, Microsoft SQL Server, Mongo DB, MySQL, AWS Redshift
Frameworks and Libraries: Scikit-learn, Pytorch, TensorFlow, Scrapy, NumPy, Pandas, Supervised and Unsupervised Machine Learning, A/B Testing
Airline Tweet Sentiment Analyzer(Python, Deep Learning)
Created social media sentiment analyzer that tracked 8 thousand review tweets using NLP and Pytorch framework with an accuracy of 72%.
Credit Card Fraud Prediction(Python)
Trained eight models to identify fraud detection with a final F1 Score of 82% leveraging CatBoost Algorithm.
Telegram App automation for repetitive Data Science Models (Python,MySQL,Tableau, Telegram)
Built Image classification model with 93% accuracy leveraging various machine learning algorithms, visualized the insights using Tableau and automated the process using telegram bot.
US Wildfires Analysis (MySQL,MongoDB)
Normalized, Modelled and Extracted insights from 2 Million records and causes of fire utilizing Joins, Aggregation and Sub-queries.
Employee Promotion Evaluation (Python)
Developed a model to predict which employees are eligible for promotion which resulted in unbiased analysis and increased employee satisfaction by 20 percent.
Chicago Crime Dataset Analysis (Pyspark)
Performed EDA and Visualization identifying most prevalent crime, number of arrests and crime growth rate from 2001 to 2016.
Data Engineer Intern, DRG Consulting Partners, Dallas, Texas Aug 2020-Dec 2020
Analyzed point of sale device logs to identify the cause of declined transactions utilizing Pyspark and Amazon S3 as storage, visualized the insights into Azure Dashboard.
Machine Learning Engineer Intern, Remote Roofing Inc, WestLake, Texas May 2020-Aug 2020
Implemented object detection and image segmentation model using Mask-RCNN to provision inspection of roof top images that augmented accuracy by 5%.
Analyzed and Visualized web scraped Property attributes from Propstream API to predict roof prices utilizing generalized linear regression and the same was pushed into PostgreSQL for internal storage.
Data Analyst, Pramati Technologies Private Limited, Bangalore, India Sep 2014-Jul 2019
Devised backup and recovery strategies, capacity planning, architecture and design, security and performance of more than 500 MS SQL Databases.
Provisioned monthly reports/dashboards on incident resolution performance helped optimize the resources & retained the service level agreement to 99%.
Formulated Excel report for Active directory User account groups streamlining access granting procedure to intranet SharePoint Websites through Identity Access Management tool.
Technical Consultant, Wipro Ltd, Mumbai, India Jan 2012-Nov 2013
Elevated satisfaction rate by 20% by providing effective problem resolution to professional/premium customers of Microsoft SharePoint Online and Windows Azure across North America region.
Created Audit review SQL scripts & security policies as part of user access review per SOX Compliance.
Master of Science - Information Technology & Management-The University of Texas at Dallas May 2021
Bachelor’s Engineering-Computer Engineering-University of Mumbai May 2011
PGP in Data Science and Machine Learning - Jigsaw Academy, University of Chicago & IBM Jan 2019
LEADERSHIP EXPERIENCE & ORGANIZATION
UT Dallas Housing-Student Assistant Dec 2019-Present