* Designed SQL star schema for efficient data retrieval and optimizing query.* Decreased data errors by 25% through comprehensive data cleaning and data filtering.* Improved data processing efficiency by 19% using PySpark scripting on large datasets.* Implemented data pipelines by connecting PowerBI, Snowflake with MySQL, Python, AWS S3 for interactive KPIs dashboards and improved performance metrics from 48% to 55%

• Boosted predictive model accuracy from 89% to 94%, reducing false negatives by20% and enhancing operational efficiency by 11% through advanced features engineering, optimizing ROC and AUC scores.• Assisted in marketing mix analysis, leading to a 10% increase in marketing ROI and influencing a 5% budget allocation increase to high-performing channels. • Managed medical image data conversion and augmentation, increased dataset size by 20% and model accuracy by 9%. Developed Flask application for demonstration, reducing client feedback time by 25% and optimized model performance using various activation and loss functions.• Merged and cleaned text datasets, reducing noise by 30% and increasing categorization accuracy by 8%.• Preprocessed text data for CRM model development using NLTK library and increased text data quality by 17% and enhanced model prediction accuracy by 7%.• Collaborated with software engineers and reduced deployment time by 20%through Dockerization, ensuring consistent environments.• Documented code, algorithms, processes, and findings, enhancing code maintainability and reducing onboarding time for new team members by 15%.