Developed an end-to-end HR analytics solution combining machine learning predictions with an interactive Power BI dashboard to analyze employee attrition patterns and retention risks. Performed exploratory data analysis (EDA), data preprocessing, and feature engineering using Python, Pandas, and SQL. Built a Random Forest classification model to predict employee attrition risk and integrated analytical insights into a multi-page Power BI dashboard. The dashboard included: • attrition trend analysis • workforce demographics • predictive risk segmentation • AI-driven root cause analysis • KPI tracking and retention insights Designed an application-style dashboard experience using custom Power BI UI components, interactive tooltips, decomposition trees, and business storytelling visuals. Key business insights generated: • Estimated $11.85M in potential attrition-related salary impact • Identified high-risk employee segments through predictive analytics • Projected retention improvement opportunities worth approximately $474K Tech Stack: Python, SQL, Power BI, Pandas, Scikit-Learn, Random Forest