-
August 2023 - Present
Research Data Analyst
School of Public Health, Indiana University
Remote, USA
Curated multiple datasets in Excel and SQL, enhancing data accuracy by 20%. Analyzed high-dimensional data with statistical modeling and machine learning in R and Python. Contributed to the development, publication, and maintenance of an R package on GitHub.
August 2023 - Present
Research Data Analyst
-
August 2022 - May 2023
Data Analyst
Institute for Digital Arts and Humanities, Indiana University
Bloomington, IN, USA
Developed automated workflows for data handling and visualization. Implemented interactive features in Tableau, boosting efficiency by 20%. Built SQL procedures for automated data extraction, enhancing accuracy by 30% and saving 20+ hours weekly. Leveraged Beautiful Soup in Python for web data extraction, reducing extraction time by 60%.
-
August 2022 - December 2022
Data Scientist
Indiana Business Research Center
Bloomington, IN, USA
Implemented supervised machine learning models (XGBoost, Light GBM, Elastic Net) with hyperparameter tuning on 1M+ data from niche, Redfin, and Melissa sources to predict house sales prices in Indiana counties with 80% accuracy in Python and R. Conducted geospatial analysis, creating 2 Tableau dashboards, reducing costs by 60%.
August 2022 - December 2022
Data Scientist
-
May 2022 - July 2022
Data Science Research Fellow
School of Public Health, Indiana University
Bloomington, IN, USA
Developed an end-to-end ETL pipeline achieving 70% accuracy in predicting lead exposure and classifying risk levels for childhood lead poisoning prevention research. Employed Random Forest and SVM models for regression and classification. Conducted data modeling and transformation on a 10k dataset using Microsoft SQL Server and Excel.
-
June 2020 - July 2020
Machine Learning Intern
TheSmartBridge
Remote, India
Developed ML predictive models (Linear Regression, Decision Tree, Random Forest) on a 5k WHO dataset to analyze life expectancy across developed and developing countries with 95% accuracy. Conducted feature selection, hyperparameter tuning, achieving 4.43 MSE. Deployed the model with Flask on a webpage using HTML/CSS for visualization.
June 2020 - July 2020
Machine Learning Intern