What problem does it solve? Raw Excel and CSV datasets often contain missing values, outliers, and inconsistent scales that break mathematical models. This Skill transforms messy data into modeling-ready datasets for MCM/ICM-style competitions under tight time constraints. ## Core Features & Use Cases - Data Cleaning: Handle missing values with mean/median imputation, interpolation, or KNN, and detect outliers using Z-Score, IQR, or Isolation Forest methods. - Normalization for Evaluation Models: Apply Min-Max, Z-Score, and vector normalization tailored for TOPSIS, AHP, and Entropy Weight Method workflows. - Feature Engineering & Statistics: Create lag features, rolling statistics, and categorical encodings, plus correlation heatmaps and distribution analysis. - Use Case: You receive a competition dataset with missing GDP values and mixed-scale indicators. Use this Skill to impute gaps, normalize benefit and cost indicators, and export a clean file ready for a TOPSIS evaluation model. ## Quick Start Clean the attached raw_data.xlsx file by imputing missing values, detecting outliers, and normalizing the indicators for a TOPSIS evaluation model.
