Bidding Behavior Classification in Online Auctions Using a Grasshopper Optimization Algorithm–Enhanced Support Vector Machine

Accurate classification of bidding behavior is crucial in understanding strategic decision-making processes within competitive and auction-based environments. This study presents a hybrid classification model that integrates the Grasshopper Optimization Algorithm (GOA) and the Support Vector Machine (SVM) to enhance the performance of bidding behavior classification. The GOA is employed to optimize the hyperparameters of the SVM, aiming to improve the model's predictive accuracy and generalization capability. The performance of the proposed model was compared with that of conventional classifiers, including Decision Tree, Logistic Regression, Naive Bayes, and standard SVM. Results indicate that the GOA-SVM outperformed all baseline models, achieving the highest accuracy (85.02 %), precision (86.45 %), and sensitivity (85.84 %). The proposed approach contributes to the advancement of intelligent bidding analysis and offers a foundation for further exploration in related classification tasks.