<![CDATA[The lack of information regarding used car prices creates obstacles for people in buying and selling vehicles because they don't understand the market prices that are used as a reference. This information is very important to know price predictions with the range of variables that can be considered. The aim is to process an algorithm model that is capable of carrying out statistics using appropriate techniques to make predictions. Prediction is a very important technique in decision making. The linear regression algorithm is a model building technique used to predict the value of a given dataset. In this study, a multiple linear regression algorithm was used to predict used car prices. The dataset used to create a prediction model with a linear regression algorithm was sourced from the Kaggle repository for used car prices and then the results were visualized in Rapminer. The prediction process uses a comparison of testing data and training data with a ratio of 90 training data and 10 testing data in the process of building the model and evaluating the model that has been produced. The result of the prediction process using the linear regression algorithm is a prediction model of Price 1637.49. The prediction model will be evaluated with 2 assessment indicators, namely RMSE and Relative Error. The results obtained from this model, in the Price category, the RMSE value is 1637.49 and the Relative Error value is 11.89%. And the application of the regression model to new data from the independent variables used is the attribute Age (Age) 24 X1, Kilometers (KM), 783764 X2, Horse power (HP) 100 X3, Transmission (Automaitc) 0 X4, Engine capacity (CC) 1500 regression equation Y = b1 + b2X1 + b3X2 + b4X3 + b5X4 +b6X5 +b7X6.]]>
Copyrights © 2024
