<![CDATA[Used cars suffer from depreciation and require reevaluation from time to time to ascertain the actual price at which the car can be purchased or sold by buyers and sellers. Car price prediction is important because of the increase in the rate of purchase of used car compared with that of new cars due to inflation, fluctuation in exchange rates, currency devaluation and so on. To address the issues of accuracy and error rate, this work suggests a hybrid feature selection approach that extracts the most crucial properties from the dataset. The most important attributes in the dataset were then used as input for the prediction phase using deep learning approach. The deep learning model's output is contrasted with that of other machine learning techniques to identify the most effective approach. In comparison to the Decision Tree and Support Vector Machine (SVM) models, which performed at 87.8% and 88.3%, respectively, the suggested hybrid feature selection using deep learning model attained an accuracy of 96.9%, according to the evaluation data. However, the other two classifiers indicate a lower error rate as compared to the ANN model.]]>
Copyrights © 2024
