◦ Designed, developed, and maintained data pipelines using Microsoft Azure, specifically leveraging Azure Data Factory for data integration and transformation.◦ Worked with Azure SQL Database and Azure Data Lake to store, process, and retrieve data, ensuring data quality and integrity through robust ELT processes.◦ Utilized Azure DevOps and Git in Databricks to streamline deployment, and monitoring of data solutions. Created user stories and branches to manage and track… Show more ◦ Designed, developed, and maintained data pipelines using Microsoft Azure, specifically leveraging Azure Data Factory for data integration and transformation.◦ Worked with Azure SQL Database and Azure Data Lake to store, process, and retrieve data, ensuring data quality and integrity through robust ELT processes.◦ Utilized Azure DevOps and Git in Databricks to streamline deployment, and monitoring of data solutions. Created user stories and branches to manage and track development tasks.◦ Collaborated with cross-functional teams to meet data requirements and support business objectives. Show less

◦ Leveraged advanced PySpark and SQL skills to analyze complex medical datasets, ensuring data integrity and accuracy.◦ Wrote efficient queries to extract key statistics and uncover significant patterns within the data.◦ Delivered presentations that highlighted strengths and weaknesses in the datasets, offering actionablerecommendations for improvements and identifying critical areas for attention.

◦ Data cleaning: Define and determine error types, search and identify error instances, correct the errors, document error instances, and error types, modify data entry procedures to reduce future errors.◦ Model checking: Manually check accuracy of mapping between physician accounts (NPPES NPI Twitter, RateMD, LinkedIn).◦ Data labeling: Tagging the data or adding metadata to make it more meaningful and informative. Matching related data from different data sources/sets. Maintaining… Show more ◦ Data cleaning: Define and determine error types, search and identify error instances, correct the errors, document error instances, and error types, modify data entry procedures to reduce future errors.◦ Model checking: Manually check accuracy of mapping between physician accounts (NPPES NPI Twitter, RateMD, LinkedIn).◦ Data labeling: Tagging the data or adding metadata to make it more meaningful and informative. Matching related data from different data sources/sets. Maintaining up-to-date information on metadata, changes, and statuses related to each data source Developing accurate, thorough, and timely data reports.◦ Automation: Connected different Excel files and sheets to continuously monitor changes in statistics. Show less

In the Data Science course, we focus extensively on Machine Learning, including supervised learning techniques such as regression and classification. We cover key concepts such as model evaluation metrics, including ROC-AUC, precision, recall, F1-score, and confusion matrix.

◦ Developed a fraud detection model using ensemble methods, including XGBoost, LightGBM, CatBoost, Gradient Boosting, and Random Forest.◦ Performed hyperparameter tuning using GridSearchCV and evaluated the models with precision, recall, and confusion matrix.◦ Achieved 98% accuracy with LightGBM, 90% accuracy with CatBoost, and 83% accuracy with XGBoost◦ Improved the model’s performance in identifying fraudulent insurance claims and optimized its ability to handleimbalanced data.

I worked on creating a data visualization model using deep learning algorithms in TensorFlow to classify eye diseases. The model achieved an accuracy of 85%, which is a significant achievement in this field. The research involved gathering and analyzing large amounts of data, using advanced machine learning techniques to identify patterns and make accurate predictions. The results of this research have the potential to improve the diagnosis and treatment of eye diseases, ultimately leading to… Show more I worked on creating a data visualization model using deep learning algorithms in TensorFlow to classify eye diseases. The model achieved an accuracy of 85%, which is a significant achievement in this field. The research involved gathering and analyzing large amounts of data, using advanced machine learning techniques to identify patterns and make accurate predictions. The results of this research have the potential to improve the diagnosis and treatment of eye diseases, ultimately leading to better health outcomes for patients. Show less