• Implemented XGBoost for advanced statistical modeling in Python, resulting in highly accurate predictions that empowered improved decision-making. • Led data analysis and predictive modeling initiatives using Python libraries (Scikit-learn, NumPy, pandas) and Spark (MLlib, PySpark), developed various advanced customer segmentation and behavior analysis algorithms, resulting in a 25% increase in customer lifetime value prediction accuracy. • Developed a sentiment analysis model using BERT that improved customer satisfaction ratings by 15% by identifying and addressing negative feedback trends. • Executed supervised learning algorithms (linear regression, decision trees, random forest) for tasks such as classification (customer churn prediction) and regression (sales forecasting). • Generated ad-hoc SQL queries using joins, database connections, and transformation rules to fetch data from legacy MySQL and SQL Server database systems.

• Utilized NLTK's stemming and lemmatization functions to reduce the dimensionality of text data by 20%, leading to faster model training and improved performance. • Established an XGBoost model that achieved a 92% accuracy rate in predicting customer churn, outperforming other machine learning algorithms by 5%. • Built a custom LLM pipeline using LangChain to create a knowledge graph from a large corpus of scientific papers, improving information retrieval by 30%. • Engineered Decision Tree, Random Forest, and SVM models, enabling targeted marketing and elevating overall customer lifetime value by 10% on average. • Provided expert data integration services using ETL tools like SSIS, streamlining data workflows and improving data quality for analytics purposes, data management reporting • Boosted SQL queries and adjusted resource allocation, improving query performance and reducing overall processing time by 20%, leading to faster data analysis and better decision-making for the organization. • Developed compelling data visualizations using R (ggplot2), Python (SciPy, Matplotlib), and Power BI to communicate insights from complex datasets.