RAHMI AZIZI, NPM 2107100008 (2024) COMPARATIVE ANALYSIS OF MACHINE LEARNING ALGORITHMS IN PREDICTING SMARTPHONE PRICES. Tugas_Akhir (Artikel) International Journal of Science, Technology & Management, 5 (4). pp. 1030-1035. ISSN 2722 – 4015 (e-ISSN)
![[img]](http://repository.ulb.ac.id/style/images/fileicons/text.png) |
Text
COVER DAN LEMBAR PENGESAHAN.pdf Download (1MB) |
|
Text
LOA.pdf Download (154kB) |
|
Text
ARTIKEL.pdf Download (214kB) |
Abstract
Rapid technological developments have made the smartphone market very competitive and dynamic. Consumers now have a variety of choices with various specifications and prices. Smartphone price prediction is important for helping consumers make purchasing decisions and for manufacturers to determine the right pricing strategy. Machine learning algorithms offer a potential solution to predict prices by utilizing specification data and other features. This study proposes the use of two machine learning algorithms, namely K-Nearest Neighbors and Random Forest, to predict smartphone prices. This study aims to analyze and compare the performance of the two algorithms in predicting smartphone prices, as well as provide recommendations on which algorithm is more effective based on the accuracy and error generated. This study employs a methodology that includes several main steps: data collection, data pre-processing, application of the proposed model, and model testing and evaluation. The results show that the Random Forest algorithm is significantly superior to K-Nearest Neighbors. Random Forest achieved an accuracy of 96.38% with a train error of 0.001003 and a test error of 0.003206, while K-Nearest Neighbors only achieved an accuracy of 59.17% with a train error of 0.009817 and a test error of 0.044094. These results indicate that Random Forest is able to handle data complexity well and provide more accurate and reliable predictions. Random Forest is a more effective algorithm than KNN for smartphone price prediction. Random Forest has a strong generalization ability and does not show any significant signs of overfitting. The results of this study can be a reference for researchers and practitioners in choosing the right machine learning algorithm for price prediction or similar problems. In addition, this study also provides insight into the importance of data preprocessing and hyperparameter tuning to obtain optimal results. Keywords : K-Nearest Neighbors, Machine Learning, Prediction, Random Forest, Smartphone.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | K-Nearest Neighbors, Machine Learning, Prediction, Random Forest, Smartphone. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software Z Bibliography. Library Science. Information Resources > ZA Information resources |
| Divisions: | Fakultas Sains Dan Teknologi > Informatika Komputer |
| Depositing User: | Unnamed user with email repository@ulb.ac.id |
| Date Deposited: | 23 Sep 2024 06:47 |
| Last Modified: | 23 Sep 2024 06:47 |
| URI: | http://repository.ulb.ac.id/id/eprint/1145 |
Actions (login required)
 |
View Item |
