The current study aims to investigate the utilization of machine learning (ML) methods in predicting cable vibration amplitude by considering various environmental factors, such as wind angle, cable angle, rainfall, and wind velocity. A diverse collection of datasets has been compiled from multiple studies conducted under different conditions. These datasets are then utilized to evaluate the performance of predictive analytics algorithm, including the Multi-layer Perceptron (MLP), Decision Tree (DT), K-Nearest Neighbors (KNN), and Random Forest (RF). The results indicate that Random Forest yields the most precise predictions of cable vibration, with R2 scores ranging from 0.90 depending on the input parameters. The analysis indicates that cable vibration is most significantly influenced by the speed of the wind, followed by cable angle and rainfall. Certain wind angles are observed to have a lesser influence on cable vibration. These findings highlight the potential of machine learning techniques in forecasting stay cable vibration and can contribute to the development of more effective design strategies for stay cable systems.