• Collaborated with cross-functional teams on a project to predict adverse drug reactions (ADRs) by integrating data from clinical trials, post-market surveillance, and spontaneous reporting systems, enhancing decision-making and safety measures.

• Extracted, cleaned, and preprocessed extensive pharmacovigilance datasets using SQL and PostgreSQL, ensuring the accuracy and consistency of over 3 million records sourced from global regulatory bodies.

• Ensured data integrity and accuracy through meticulous cleaning and preprocessing with Python (pandas, NumPy), achieving 99.5% accuracy in the final ADR datasets, thereby enhancing the reliability of subsequent safety analyses.

• Built machine learning models using Python (scikit-learn, pandas, NumPy) to predict ADRs from historical pharmacovigilance data, attaining 80% accuracy in early identification of potential safety risks.

• Utilized advanced statistical techniques such as survival analysis and regression to pinpoint factors contributing to ADRs, leading to a 10% improvement in regulatory compliance and more precise identification of high-risk patient groups.

• Developed time-series forecasting models (ARIMA, Exponential Smoothing) to predict future ADR trends, facilitating proactive risk management, and potentially saving $2 million in post-market regulatory penalties and recalls.

• Created interactive Tableau dashboards for real-time monitoring of ADR trends and safety metrics, reducing reporting delays by 15% and supporting data-driven decision-making at the executive level.

• Designed and implemented A/B testing frameworks to assess the effectiveness of pharmacovigilance interventions, resulting in a 12% improvement in ADR detection accuracy and faster safety response times.

• Leveraged AWS Redshift and S3 for efficient data storage, enabling scalable processing of large pharmacovigilance datasets and reducing data retrieval times by 30%.

Tools: SQL, PostgreSQL, Python (Programming Language), NumPy, Pandas, Scikit-Learn, Regression Analysis, ARIMA, Exponential Smoothing, Tableau, A/B Testing, AWS Redshift, Amazon S3

• Designed and developed a comprehensive real-time supply chain visibility dashboard using Power BI, integrating data from multiple sources, including logistics, warehouse management, and manufacturing systems, to provide stakeholders with a unified, interactive view of the supply chain.

• Implemented advanced data integration solutions leveraging AWS services such as Amazon S3 and AWS Glue to efficiently extract, transform, and load (ETL) large volumes of supply chain data from disparate systems, achieving a 40% improvement in data processing speed and accuracy.

• Engineered custom data pipelines and optimized SQL databases to ensure seamless data flow and real-time updates, enabling accurate tracking of inventory levels, order statuses, and shipment progress, while reducing data retrieval times by 30%.

• Applied statistical and machine learning techniques to forecast potential bottlenecks and delays in the supply chain, resulting in the proactive identification of issues and a 15% improvement in overall operational efficiency.

• Developed automated reporting mechanisms using Excel macros and VBA scripts, streamlining data extraction, and reporting processes, and reducing manual errors by 25%, ensuring stakeholders received accurate, timely supply chain insights.

• Enhanced dashboard functionality by incorporating predictive analytics for inventory and demand forecasting, reducing stockouts and excess inventory by 10%, and improving the overall cost-efficiency of the supply chain.

• Promoted cross-functional collaboration in an Agile environment, actively contributing to sprint cycles and continuously iterating on the dashboard based on feedback from key stakeholders, leading to improved supply chain performance.

Tools: Amazon S3, AWS Glue, Extract, Transform, Load (ETL), SQL databases, Microsoft Power BI, Machine Learning, Statistical Data Analysis, Excel macros, VBA scripts, Predictive Analytics, Agile Environment.