SETYAWAN, WAHYU ADI (2023) CAR PRICE PREDICTION USING NEURAL NETWORK AND KNN. Other thesis, Universitas Katholik Soegijapranata Semarang.
![[img]](http://repository.unika.ac.id/style/images/fileicons/text.png) |
Text
17.K1.0042-WAHYU ADI SETYAWAN-COVER_a.pdf Download (365kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-BAB I_a.pdf Download (114kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-BAB II_a.pdf Restricted to Registered users only Download (122kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-BAB III_a.pdf Download (113kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-BAB IV_a.pdf Download (185kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-BAB V_a.pdf Download (300kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-BAB VI_a.pdf Download (109kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-DAPUS_a.pdf Download (175kB) |
|
Text
17.K1.0042-WAHYU ADI SETYAWAN-LAMP_a.pdf Download (157kB) |
Abstract
The average selling price of new vehicles has increased by around 18% per year over the last ten years. The question of how much a car costs each year has no definitive answer. Car prices can vary depending on the make, model, and year. However, some general trends can be anticipated. Many automakers anticipate an increase in car prices as the cost of raw materials such as steel and aluminum rises. As you can see, many different factors influence the price of a new car. Automobiles are generally more expensive in cities than in rural areas. This can be attributed to the higher costs of maintaining and operating vehicles in cities. The author will use the Orange data mining program using K-Nearest Neighbor and Neural Network algorithms to estimate car prices based on prior exposure. Data from the Kaggle website will be used in this approach. Two techniques will be used to process the data: the first is the K-Nearest Neighbor technique, and the second is the Neural Network technique. Following the completion of the prediction process, it was discovered that the MSE value of the Neural Network model is lower than that of the KNN model. After three trials, this result was reached by comparing the variance between the training data and the testing data. The differences in comparison are 70%–30%, 80%–20%, and 90%–10%. The Neural Network generates the least amount of value out of the three options.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | 000 Computer Science, Information and General Works > 004 Data processing & computer science |
| Divisions: | Faculty of Computer Science > Department of Informatics Engineering |
| Depositing User: | mr AM. Pudja Adjie Sudoso |
| Date Deposited: | 04 Apr 2023 06:00 |
| Last Modified: | 04 Apr 2023 06:00 |
| URI: | http://repository.unika.ac.id/id/eprint/31394 |
Actions (login required)
 |
View Item |
