Light pollution is an increasingly prevalent issue that harms the health of human beings, animals, and plants. Light pollution causes disruption that alters the habitats of nocturnally active species. As nocturnal insects are lured to artificial light sources, the consequences can be fatal. Moths are nocturnal insects that have an abnormal sensitivity to artificial light. Artificial night exposure has been identified as one of the main causes of the rapid decrease in moth populations. Artificial night lighting causes moths to spend shorter periods of feeding than moths in the dark. Therefore, artificial lighting shortens feeding periods, heightens sub-lethal effects, and increases moth mortality. In this research, to analyze the effects of light pollution and for the observation of foraging by moths, different machine learning models have been used in the ‘Data Moth Foraging’ dataset. To perform analysis, Decision Tree, Random Forest, KNN, and XGBoost have been used. SMOTE, Borderline-SMOTE, and SMOTE-Tomek have been applied to balance the imbalanced dataset, which has considerably improved evaluation metrics. Borderline-SMOTE outperformed SMOTE and SMOTE-Tomek, with Decision Tree, Random Forest, and XGBoost achieving 84% macro-averaged F1 score and KNN achieving 83%. Explainable AI techniques such as LIME, SHAP, and ELI5 have also been applied to explain and analyze the models’ predictions.