<![CDATA[In motor vehicles, including cars, the battery plays an important role, namely as a place to store electrical energy and as an electric voltage stabilizer when the engine is turned on. In general, motorized vehicle users do not know the condition of the battery in their vehicle. Even though the use of battery batteries that are already in poor condition can interfere with vehicle performance. In battery replacement services such as after-sales service, the process of checking and replacing battery batteries takes a relatively long time. This can be caused by high service volume, lack of worker reliability, lack of responsiveness to the complexity of the inspection. This research aims to build a prediction model for battery battery replacement time quickly. To meet these needs, a Machine Learning approach can be used. Machine Learning uses historical replacement data to make predictions of replacement time. Machine Learning algorithms that can be used for prediction are XGBoost and Random Forest. This research uses ensemble learning techniques to combine the two models. Based on the evaluation results, it can be concluded that the model built with ensemble learning has better prediction results than a single model. Evaluation results with MSE on the ensemble bagging model have the lowest error values of 145,448. The MAPE, MAE, and RMSE evaluations on the ensemble boosting model have the lowest error values of 11.56 %, 43.80 and 38,760.]]>
Copyrights © 2024
