Big data classification is a challenging task, especially when dealing with imbalanced datasets where minority class instances are significantly underrepresented. Traditional machine learning models often exhibit bias toward the majority class, leading

Abstract

Big data classification is a challenging task, especially when dealing with imbalanced datasets where minority class instances are significantly underrepresented. Traditional machine learning models often exhibit bias toward the majority class, leading to suboptimal classification performance. This research proposes a novel optimization-tuned machine learning framework that enhances classification accuracy in imbalanced big data. The proposed approach integrates ensemble learning with an innovative hybrid
optimization algorithm that combines Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) to optimize hyperparameters dynamically. The study employs various benchmark datasets and evaluates the framework using performance metrics such as Precision, Recall, F1-score, and the Area Under the Receiver Operating Characteristic Curve (AUC-ROC). Experimental results demonstrate that the proposed approach outperforms conventional machine learning methods in terms of classification
accuracy and minority class detection. The findings contribute to the advancement of imbalanced big data classification by providing an optimized and scalable solution.