<![CDATA[The rapid development of smartphones has led to a wide variety of specifications and price ranges, making it difficult for consumers to choose devices objectively. Performance differences influenced by hardware specifications and pricing require a data-driven classification approach. This study aims to classify smartphones based on performance and price using the K-Nearest Neighbor (KNN) algorithm. The dataset consists of 981 smartphone records obtained from Kaggle, including attributes such as processor speed, number of cores, RAM, internal storage, battery capacity, camera resolution, rating, and price. Data preprocessing includes handling missing values and feature normalization using StandardScaler. Smartphones are categorized into three classes: Budget, Midrange, and Flagship. The model evaluation uses confusion matrix, accuracy, precision, recall, and F1-score. Experimental results show that the KNN algorithm achieves an accuracy of 92%, indicating that it is effective for smartphone classification problems.]]>
Copyrights © 2026
