A Firefly Optimization Algorithm for Hyperparameter Tuning of the Support Vector Classifier to Predict Water Potability

Clean water is essential for human health and life, and assessing its potability is critical for safeguarding public well-being. Machine Learning (ML) algorithms have been widely used for water potability classification based on various water quality parameters. However, the performance of these models strongly depends on effective hyperparameter tuning, which remains both challenging and resource-intensive. This study addresses this issue by proposing the Firefly Optimization Algorithm (FOA) to optimize the Support Vector Classifier (SVC) for water potability classification. Traditional hyperparameter tuning methods, such as GridSearchCV and RandomizedSearchCV, often lack the efficiency and effectiveness needed for achieving optimal model performance. In contrast, the proposed FOA-based approach provides a robust solution, demonstrating superior results compared with traditional methods. Model performance was evaluated using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). The FOA-tuned SVC achieved an accuracy of 0.6773 and an AUC of 0.7065, outperforming models tuned with conventional methods. These findings highlight the potential of nature-inspired optimization techniques, such as the Firefly algorithm, to enhance ML model performance and offer a promising approach to water potability classification.