Owing to the increasing popularity of electric vehicles (EVs), the aging behavior of lithium-ion batteries has become one of the most important factors influencing the overall performance and lifetime of EVs. This study is concerned with the dynamic aging of lithium-ion batteries, and research is performed using machine learning methods with Artificial Neural Networks and Random Forest models. The dataset analyzed here contains important parameters that are obtained during the operation of the battery, such as measured time (s), voltage measured (V), measured current, temperature measured, and capacity (Ah). These parameters were obtained during actual driving to reflect the dynamic properties of EV battery usage. An Artificial Neural Network (ANN) was used to capture complex nonlinear patterns and relationships in the dataset to predict battery aging from input parameters. Moreover, the Random Forest (RF) model is applied to benefit from ensemble learning and cope with the multi-dimensionality of the data. This research will provide insights into the effects of dynamic conditions on the aging mechanisms and disposal of high-capacity batteries for electric vehicles and the development of prediction models that permit reliable estimation of the remaining life of lithium-ion batteries. It is hoped that the machine learning models proposed in this study will contribute to the optimization of battery management systems, enabling the more efficient and sustainable use of electric vehicle batteries.