• Developed a scalable hotel recommendation system using machine learning on the Databricks platform, boosting user engagement by 8%.• Applied machine learning techniques including Random Forest and boosting methods such as XGBoost and LightGBM to enhance recommendation accuracy by 11% in terms of F1 score.• Implemented MLOps practices including CI/CD pipelines, automated model retraining, and monitoring, ensuring continuous delivery and high availability.• Enhanced recommendation accuracy through feature engineering, model optimization, and real-time data integration, improving overall user satisfaction.• Conducted extensive data cleaning and exploratory data analysis (EDA) to identify patterns, trends, and anomalies, ensuring high-quality and reliable data for model training.• Managed data warehouse operations using technologies such as Snowflake and SQL, optimizing data storage and retrieval processes to support efficient analytics and reporting.

• Conducted comprehensive data analysis on clinical trial data to evaluate drug efficacy, aiding in criticaldecision-making in the Life Sciences department, leading to a 10% improvement in clinical trial assessments.• Performed extensive exploratory data analysis (EDA) to identify trends, patterns, and anomalies in clinical data, ensuring robust and reliable insights.• Leveraged Tableau to design and develop interactive, user-friendly data visualizations and dashboards for clinicians, facilitating increase in data-driven decisions.• Created detailed dashboards focusing on key drug efficacy metrics, including adverse effects, quality of life, and progression-free recovery, ensuring data-driven clinical assessments.• Developed four targeted dashboards for effective stratification, in-depth analysis of test subject demographics, and thorough examination of adverse effects, enhancing the clarity and usability of clinical trial data.