Remaining use life (RUL) prediction is becoming more and more popular as a way to allay worries about security and dependability of lithium-ion batteries in electric cars. Even though battery operational characteristics are thoroughly recorded, the current prediction methodologies for evaluating battery performance are inadequate. To address the issues of inadequate local feature learning and insufficient capacity to handle large datasets, a data-driven prediction method of machine learning algorithms is proposed. The intention of this paper is to use specific machine learning techniques to improve prediction resilience and accuracy. Selected machine learning techniques are evaluated for accuracy prediction using real life battery cycle data set from the Hawaii National Energy Institute (HNEI). For each of the ML methods, performance error indices are computed, including Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R-Squared. Relevant inferences are then exhibited, highlighting the prospective of battery RUL prediction near most accurate values. The findings demonstrate that, in comparison to other approaches, the random forest method is more resilient and considerably increases RUL prediction accuracy while reducing prediction error.