Accurate estimation of the state of charge (SOC) of lithium-ion battery packs remains challenging due to inconsistencies among battery cells. To achieve precise SOC estimation of battery packs, first, the battery pack's internal resistance and capacity should be accurately identified. Then, a suitable SOC estimation algorithm can be applied to predict the SOC of the battery pack. This study aims to investigate the application of advanced machine learning algorithms, such as long short-term memory recurrent neural networks and transfer learning, to improve the accuracy of SOC estimation. The proposed method is expected to provide a more accurate and reliable SOC estimation, which is essential for the safe and efficient operation of electric vehicles.