Abstract

This study applies machine learning classification techniques to predict passenger displacement events based on corrupted data retrieved from a hypothetical interstellar spacecraft mission. Using a cleaned and preprocessed dataset containing demographic, behavioral, and exposure-related features, we compare the performance of three classification models: Random Forest, Support Vector Machine (SVM), and XGBoost. Each model is trained on 80% of the data and evaluated on the remaining 20% using precision, recall, f1-score, and accuracy metrics. The SVM model shows the most notable improvement after feature selection, achieving a balanced performance across metrics. Meanwhile, Random Forest and XGBoost models maintain consistent and robust accuracy above 80% on both training and testing sets. Feature importance analysis also supports the interpretability of the models, particularly in Random Forest and XGBoost. The comparative analysis demonstrates that ensemble-based methods such as Random Forest and XGBoost are more effective in handling the complexity of the dataset, making them suitable for predictive tasks in high-dimensional, partially incomplete data scenarios.

Concepts :

Access to Document

Citations by Year