PawarMukesh/Employee-Performance-Analysis

Implements a complete ML pipeline using SVM, Random Forest, and Multilayer Perceptron classifiers on a 1,200-row employee dataset with 28 features (numeric, ordinal, and categorical). Applies manual and frequency encoding for categorical conversion, IQR-based outlier handling, and square root transformation for skewed distributions, achieving 95.8% accuracy with the neural network model. Performs univariate, bivariate, and multivariate analysis using Matplotlib and Seaborn to identify key performance drivers (environment satisfaction, salary hikes, work-life balance) and generate department-specific insights.

No commits in the last 6 months.