Sidhdesh
Sidhdesh Gupta
------------ | ------------ |------------/in/sidhdeshgupta
EDUCATION
Master of Science - Business Analytics and Project Management Aug 2019 - Dec 2020
University of Connecticut School of Business, Hartford, CT GPA 3.70
Bachelor of Engineering - Information Technology Aug 2010 - Jun 2014
Rajiv Gandhi Proudyogiki Vishwavidyalaya, Bhopal, India GPA 3.78
SKILLS
Programming Languages: SQL, Python (NumPy, Pandas, scikit-learn, seaborn, matplotlib PySpark), R (ggplot2, dplyr) , Unix, Java
Database: Oracle, MYSQL, Teradata, SQL Server, Redshift, Snowflake, Hadoop, Hive, Pig, Sqoop
Tools: Tableau, SAS JMP, Visio, MS Office, SAS Enterprise Miner, Informatica Power Center, Business Objects, Eclipse, Power BI
Analytical Skills: Data cleaning, Data Analysis, Data Mining, Hypothesis Testing, Statistical Analysis and Modeling, Machine Learning, Clustering, Logistic and Linear Regression, Time Series Forecasting, NLP, CNN, XGBoost, Text Analytics, Data Visualization
Cloud Environment: AWS, Azure, EC2, CC2, S3, Athena, Glue, Google Cloud Platform, Big Query
EXPERIENCE
Commonwealth Care Alliance| Business Solution Intern| Python | Talend | Looker Boston, MA (Sep 2020 – Present)
• HealthCare Analytics: Architectured the data dictionary, schema & data models for pharmacy and claims data. Based on the analyses, transformed & loaded the data into the data warehouse. Built dashboards to monitor key performance indicators
• Clustering: Segmented members using K-means clustering to develop platform for Diagnosis Recommendation system.
Exonetics| Data Science Intern| Python | Statistical Analyses Huntsville, Al (May 2020 – Aug 2020)
• Sports Analytics: Extracted unlabeled biomechanical data from sensors (fitted to garments) and then extracted features of athlete’s fitness. Performed exploratory data analysis to find patterns and correlations between different knee motions. Implemented Naïve Bayes model with an accuracy of 88.4% to classify athletes as injured/non-injured
UCONN Grad Consulting Club, University of Connecticut | Analytics Consultant Hartford, CT (Oct 2019 – Mar 2020)
• Web Analytics: Used unsupervised machine learning to streamline the marketing process by navigating traffic data for over 100,000 potential customers and identifying key segments to target. Tracked and reported website behaviors and campaign performance for client leveraging Google Analytics
Tata Consultancy Services | IT Data Analyst | Oracle | MS Azure | Python | Tableau Mumbai, India (Jun 2018 – Jul 2019)
• Data Engineering: Developed a Python script and data pipeline to migrate terabytes volumes of PeopleSoft data from Oracle to Azure. Reduced manual labor work by 148 hours in processing business of a single client
• HR Analytics: Predicted the employees who have more propensity of leaving the company based on the employee data. Visualized the insights & recommendations to various stakeholders to aid strategic decisions for improvements in employee satisfaction
Sr. Software Engineer | MS Power BI | Teradata | Unix | Agile Jan 2017 - May 2018
• Data Engineering: Maintained end to end data flow in the enterprise data warehouse using Teradata to support transactions at user level. Upgraded the Informatica tool for the production server in Enterprise Data warehouse, saving $47M for client
• Dashboards: Created an interactive dashboard to track real-time updates using PowerBI to help business partners track major KPIs (Growth Rates, Revenue, Profit Margin, Customer Retention) and assisted them in decision making process
Software Engineer | Java | MYSQL | Unix | Informatica Nov 2014 – Dec 2016
• ETL/WebApp: Created web applications and workflows for GE’s fleet business across eight European countries, that transformed the data tables, loaded data into the Datawarehouse. Working on change enhancements were other tasks
• Process Improvement: Created a UNIX script to automate the vehicle image upload process, in a fleet project that resulted in saving 2 hours for the tedious process. Received the ‘Young Achiever Award’ from TCS management for the same
ACADEMIC PROJECTS Hartford, CT
Potoo Data Challenge | MS Excel | SAS Enterprise Miner | Python | Tableau Aug 2019 – Oct 2019
• Created oracle database with the stock price of the publicly listed companies on amazon. Deep dived stock prices and stock indicators to create dashboards to find insights and detect the impact of stocks on sales.
Predicting Restaurant Ratings | Predictive Modeling | SAS JMP Sep 2019 – Nov 2020
• Analyzed 1.1M rows of data which included the restaurants from 31 European countries. Predicted the ‘Ratings’ of restaurants using an ensemble model of Naïve Bayes and logistic regression models with an accuracy of 82.8%
Time Series Forecasting | Sentiment Analysis |Python | Web scraping Feb 2020 – Apr 2020
• Founded Zombie companies in the COVID-19 situation & forecasted their Stock prices by using an Arima model with an 80.8% accuracy. Used web scraping to integrate the data. Did sentiment analysis to find patterns in tweets on twitter
Sidhdesh Gupta
------------ | ------------ |------------/in/sidhdeshgupta
EDUCATION
Master of Science - Business Analytics and Project Management Aug 2019 - Dec 2020
University of Connecticut School of Business, Hartford, CT GPA 3.70
Bachelor of Engineering - Information Technology Aug 2010 - Jun 2014
Rajiv Gandhi Proudyogiki Vishwavidyalaya, Bhopal, India GPA 3.78
SKILLS
Programming Languages: SQL, Python (NumPy, Pandas, scikit-learn, seaborn, matplotlib PySpark), R (ggplot2, dplyr) , Unix, Java
Database: Oracle, MYSQL, Teradata, SQL Server, Redshift, Snowflake, Hadoop, Hive, Pig, Sqoop
Tools: Tableau, SAS JMP, Visio, MS Office, SAS Enterprise Miner, Informatica Power Center, Business Objects, Eclipse, Power BI
Analytical Skills: Data cleaning, Data Analysis, Data Mining, Hypothesis Testing, Statistical Analysis and Modeling, Machine Learning, Clustering, Logistic and Linear Regression, Time Series Forecasting, NLP, CNN, XGBoost, Text Analytics, Data Visualization
Cloud Environment: AWS, Azure, EC2, CC2, S3, Athena, Glue, Google Cloud Platform, Big Query
EXPERIENCE
Commonwealth Care Alliance| Business Solution Intern| Python | Talend | Looker Boston, MA (Sep 2020 – Present)
• HealthCare Analytics: Architectured the data dictionary, schema & data models for pharmacy and claims data. Based on the analyses, transformed & loaded the data into the data warehouse. Built dashboards to monitor key performance indicators
• Clustering: Segmented members using K-means clustering to develop platform for Diagnosis Recommendation system.
Exonetics| Data Science Intern| Python | Statistical Analyses Huntsville, Al (May 2020 – Aug 2020)
• Sports Analytics: Extracted unlabeled biomechanical data from sensors (fitted to garments) and then extracted features of athlete’s fitness. Performed exploratory data analysis to find patterns and correlations between different knee motions. Implemented Naïve Bayes model with an accuracy of 88.4% to classify athletes as injured/non-injured
UCONN Grad Consulting Club, University of Connecticut | Analytics Consultant Hartford, CT (Oct 2019 – Mar 2020)
• Web Analytics: Used unsupervised machine learning to streamline the marketing process by navigating traffic data for over 100,000 potential customers and identifying key segments to target. Tracked and reported website behaviors and campaign performance for client leveraging Google Analytics
Tata Consultancy Services | IT Data Analyst | Oracle | MS Azure | Python | Tableau Mumbai, India (Jun 2018 – Jul 2019)
• Data Engineering: Developed a Python script and data pipeline to migrate terabytes volumes of PeopleSoft data from Oracle to Azure. Reduced manual labor work by 148 hours in processing business of a single client
• HR Analytics: Predicted the employees who have more propensity of leaving the company based on the employee data. Visualized the insights & recommendations to various stakeholders to aid strategic decisions for improvements in employee satisfaction
Sr. Software Engineer | MS Power BI | Teradata | Unix | Agile Jan 2017 - May 2018
• Data Engineering: Maintained end to end data flow in the enterprise data warehouse using Teradata to support transactions at user level. Upgraded the Informatica tool for the production server in Enterprise Data warehouse, saving $47M for client
• Dashboards: Created an interactive dashboard to track real-time updates using PowerBI to help business partners track major KPIs (Growth Rates, Revenue, Profit Margin, Customer Retention) and assisted them in decision making process
Software Engineer | Java | MYSQL | Unix | Informatica Nov 2014 – Dec 2016
• ETL/WebApp: Created web applications and workflows for GE’s fleet business across eight European countries, that transformed the data tables, loaded data into the Datawarehouse. Working on change enhancements were other tasks
• Process Improvement: Created a UNIX script to automate the vehicle image upload process, in a fleet project that resulted in saving 2 hours for the tedious process. Received the ‘Young Achiever Award’ from TCS management for the same
ACADEMIC PROJECTS Hartford, CT
Potoo Data Challenge | MS Excel | SAS Enterprise Miner | Python | Tableau Aug 2019 – Oct 2019
• Created oracle database with the stock price of the publicly listed companies on amazon. Deep dived stock prices and stock indicators to create dashboards to find insights and detect the impact of stocks on sales.
Predicting Restaurant Ratings | Predictive Modeling | SAS JMP Sep 2019 – Nov 2020
• Analyzed 1.1M rows of data which included the restaurants from 31 European countries. Predicted the ‘Ratings’ of restaurants using an ensemble model of Naïve Bayes and logistic regression models with an accuracy of 82.8%
Time Series Forecasting | Sentiment Analysis |Python | Web scraping Feb 2020 – Apr 2020
• Founded Zombie companies in the COVID-19 situation & forecasted their Stock prices by using an Arima model with an 80.8% accuracy. Used web scraping to integrate the data. Did sentiment analysis to find patterns in tweets on twitter