INTAN FADILLA HASIBUAN, NPM 2107100018 (2024) COMPARATIVE ANALYSIS OF K-NEAREST NEIGHBORS AND DECISION TREE METHODS IN DETERMINING STUDENTS’ PURCHASE INTEREST IN MACBOOK LAPTOPS. Tugas_Akhir (Artikel) International Journal of Science, Technology & Management, 5 (5). pp. 1122-1128. ISSN 2722 – 4015 (e-ISSN)
![[img]](http://repository.ulb.ac.id/style/images/fileicons/text.png) |
Text
COVER FULL.pdf Download (3MB) |
|
Text
LOA.pdf Download (510kB) |
|
Text
ARTIKEL.pdf Download (339kB) |
Abstract
In the context of increasingly competitive technology markets, companies need to know consumer preferences accurately to optimize product offerings and increase sales. Two classification methods that are often used in data mining, namely K-Nearest Neighbors and Decision Tree, have their own advantages and disadvantages. This study proposes a solution that involves processing student data using both classification methods to identify the most accurate and effective method for identifying purchase intentions. This study aims to compare the performance of the two methods in determining student purchase intentions for MacBook laptops. The research methodology includes collecting data from 100 students covering various factors such as user experience, design and portability, technical specifications, price, and security. This data is then classified using the K-Nearest Neighbors and Decision Tree methods. Furthermore, a confusion matrix is used to provide a more detailed picture of the performance of the two methods. The results of the study show that the Decision Tree method has a higher accuracy (91%) compared to K-Nearest Neighbors (88%). In addition, Decision Tree excels in other metrics such as precision (87.18% vs. 85.71%), recall (89.47% vs. 85.71%), specificity (91.94% vs. 89.66%), and F1-Score (88.31% vs. 85.71%). The decision tree also has a higher NPV value and lower FPR and FNR rates than K-Nearest Neighbors, indicating that it is superior in avoiding misclassification. The study's conclusion is that the Decision Tree method is more effective and accurate than K-Nearest Neighbors in determining students' purchase intentions for MacBook laptops. The decision tree shows better performance in almost all evaluation metrics, making it a more reliable method to use in consumer data analysis. The results of this study are expected to help companies choose a more appropriate and effective analysis method for their marketing strategies, as well as provide a basis for further research in the field of consumer purchase intention classification. Keywords : Data Mining, Decision Tree, K-Nearest Neighbors, MacBook Laptop and Purchase Interest.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Data Mining, Decision Tree, K-Nearest Neighbors, MacBook Laptop and Purchase Interest. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Z Bibliography. Library Science. Information Resources > ZA Information resources Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources |
| Divisions: | Fakultas Sains Dan Teknologi > Informatika Komputer |
| Depositing User: | Unnamed user with email repository@ulb.ac.id |
| Date Deposited: | 11 Oct 2024 09:28 |
| Last Modified: | 11 Oct 2024 09:28 |
| URI: | http://repository.ulb.ac.id/id/eprint/1177 |
Actions (login required)
 |
View Item |
