This is my profileContact via CazVidAbhinav
Data Scientist with 5+ years in healthcare & analytics
Contact
Competencies
Develops interactive dashboards and reports using tools like Tableau and Excel to communicate insights effectively.
Designs and implements machine learning models such as logistic regression, XGBoost, leveraging feature engineering and statistical testing.
Applies data models and pipelines to clinical datasets, improving data retrieval and predictive accuracy in healthcare contexts.
Builds and automates data pipelines using SQL, Spark, Python, and ETL processes to support analytical workflows.
Performs statistical tests and outlier detection to ensure data quality and robustness of machine learning models.
Education
Summary
Experienced Data Scientist with a strong background in developing scalable data pipelines, predictive models, and data visualization tools within healthcare and financial domains. Skilled in Python, SQL, R, and modern frameworks, committed to delivering data-driven insights to inform...
Key Achievements
- Built cohort extraction pipelines using Spark SQL and OMOP data models at Stony Brook University, reducing retrieval time by 30% across 1B+ records.
- Enhanced predictive model accuracy by 17% with logistic regression and XGBoost, utilizing feature relevance testing on over 1 million patient records.
- Automated anomaly detection processes with PySpark, pandas, and thresholds, identifying over 95% of data quality issues before modeling.
Experience
Research Assistant (Data Scientist)
Built cohort extraction pipelines using Spark SQL and OMOP data models in N3C, improving retrieval time by 30% across 1B+ clinical records., Boosted predictive accuracy by 17% using logistic regression and XGBoost, applying chi-square tests for feature relevance and p-value consistency on 1M+...
Data Analyst
Automated 15 financial KPI metrics using SQL Server, Python, and Star Schema, reducing monthly reporting time by 7 days and accelerating report refresh cycles and supporting data governance compliance., Conducted detailed analysis of customer territories and market opportunities using PivotTables...