PREDICTIVE ANALYSIS OF OPERATIONAL RISK IN CONTAINERS AT THE PORT OF SANTOS

Abstract

This paper proposes a predictive operational risk model to prioritize container inspections at the Port of Santos. Using a synthetic dataset built from realistic parameters, we applied preprocessing (One‑Hot, scaling), PCA for dimensionality reduction, K‑Means clustering and supervised classifiers (KNN, SVM). The SVM achieved 93.4% accuracy on stratified validation. We discuss practical implications, limitations of synthetic data and pathways for integrating the model into port operational routines