Mohamad Iqbal Ulumando
Used motorcycle prices in the market often fluctuate and are influenced by various factors such as brand, type, year of manufacture, engine capacity, mileage, vehicle condition, and tax status. In Kupang City, the determination of used motorcycle prices is generally still performed manually based on seller estimates or market conditions, which can lead to significant price differences. Therefore, a method is needed to estimate used motorcycle prices more objectively and accurately. This research seeks to develop a model for predicting used motorcycle prices employing the Random Forest algorithm. The dataset used consists of 200 used motorcycle records collected from used motorcycle sales data in Kupang City. The data undergoes a preprocessing stage before being used for model development. Furthermore, the dataset is partitioned into training data and testing to build evaluate prediction. The evaluation results show a Mean Absolute Error (MAE) of Rp.4,418,477, a Mean Squared Error (MSE) of 26,617,157,710,315, and a Root Mean SquSquared Error (RMSE) of Rp.5,159,181. The findings suggest that the Random Forest predict motorcycle prices with reasonably acceptable error rate, making it a useful approach for estimating used motorcycle prices based on vehicle attributes.