With a passion for turning complex data into clear insights, I help organizations leverage data to drive smarter strategies. My work spans predictive modeling, visualization, reporting automation, and customer analytics — powered by Python, SQL, R, Tableau, and Power BI.
To bridge the gap between data and decision-making, empowering organizations with transparency and clarity through advanced analytics and machine learning.
Deliver data solutions that not only meet business goals but also foster a culture of data-driven thinking and innovation.
Expert in uncovering trends through statistical analysis and creating visual dashboards in Tableau, Power BI, and R to support executive decision-making.
Designed classification and regression models to forecast outcomes like customer churn and service demand using Python, R, and advanced SQL.
Applied time-series forecasting, logistic regression, and trend modeling to anticipate user behavior, optimize resource allocation, and reduce churn rates.
Applied logistic regression, time-series forecasting, and multivariate analysis to solve business problems like churn prediction and demand forecasting with measurable impact.
Built executive dashboards using Power BI and Tableau, enabling real-time insights and reducing reporting time by 35% through automation and centralized access.
Experienced in SQL Server, PostgreSQL, and Alteryx for ETL workflows, data cleansing, and integrating disparate data sources to build consistent, analytics-ready datasets.
Engineered a regression pipeline using Python, achieving an R² score of 0.75. Conducted exploratory data analysis and multivariable plotting to identify the top 6 predictors influencing insurance premium costs. Helped uncover cost-saving opportunities through detailed model interpretation and visualization.
Built a logistic regression-based churn prediction model using customer data. Reduced churn rate by 15% through targeted scoring. Utilized Salesforce visualizations to identify and eliminate retention bottlenecks, resulting in a 20% increase in customer satisfaction and loyalty metrics.
Led the development of a sentiment analysis pipeline using Python and NLP techniques. Improved classification accuracy by 31% through automated labeling and clustering. Extracted 9 key sentiment groups from over 6,000 text records using unsupervised learning, delivering insights to enhance stakeholder understanding of audience feedback.