Classification and Comparative Analysis of Earth's Nearest Objects using Machine Learning Models

This research aims to analyze and visualize the NASA - Nearest Earth Objects dataset in order to classify asteroids into hazardous and non-hazardous categories. The work is carried out to unleash the mysteries in space. Researchers have always been striving to unleash something hidden in the layers of space. Further, it also necessitates determining the level of hazard of the space body. Hence, the authors in this paper aim to employ the efficacy of machine learning to handle such astronomical problems. During the experimental setup, the authors have considered the NASA- Nearest Earth Objects available on Kaggle. The authors also demonstrated the data through various visualization graphs that enable the reader to easily analyze the dataset. The ultimate goal is to design an efficient prediction model that exhibits a good generalization. The authors also generated a classification report and plotted a confusion matrix. The models are analyzed based on their accuracy which establishes the effectiveness and efficiency of machine learning algorithms to address such problems.