AI Summary & Key Takeaways
AI InsightIn addition, at another stage of the study, the price range for 1000 devices with different features was determined by using a test dataset that was not labeled, and the results produced by both models were compared.
📌 3 Key Takeaways
Abstract
The aim of this study was to compare the classification performances of K-nearest neighbors (KNN) and Deep Neural Networks (DNN) models in a dataset. For this purpose, the “mobile price forecast" dataset has been selected. It includes 20 different features of mobile phones such as battery power, Bluetooth function, memory capacity, screen size. The problem presented in the dataset is to determine the price range class before the mobile phones are released. Such a forecast will help companies that manufacture mobile devices to estimate the price of their mobile phones in a more convenient method to compete against their competitors in the market. In the implementation phase of the study, the KNN and DNN models were created in Python 3.6 with the Sklearn and Keras libraries. The classification performances of the models were determined using F-1 score, accuracy, recall and accuracy measurements. As a result of the study, validation data was classified with 92% accuracy using the trained DNN model. In addition, at another stage of the study, the price range for 1000 devices with different features was determined by using a test dataset that was not labeled, and the results produced by both models were compared.