Pendekatan Machine Learning untuk Analisis dan Visualisasi Data Jembatan Timbang

In this research, a machine learning approach, especially a decision tree model, is implemented to improve the analysis and visualization of weighbridge data in Indonesia. The evaluation results show that the decision tree model provides better insight in predicting the carrying capacity, dimensions and loading procedures of vehicles. The advantage of this model lies in its combination of low Mean Squared Error (MSE) and high R-squared, indicating its effectiveness in capturing data variance and providing accurate predictions. The use of decision tree models can be a valuable tool in improving the visualization of bridge weighing data, allowing users to gain additional insights and understand the complex dynamics within the data. In addition, the model's adaptability to various types of data makes it a versatile analysis tool. The positive implications of using this model open up opportunities to understand more deeply the logic of predictions and make more informed decisions. As a suggestion, increasing the number and quality of weighing equipment, wider application of information and communication technology, human resource training, and cross-sector collaboration can further strengthen weighbridge management in Indonesia.