Comparative Analysis of Mobile Price Classification Using Feature Engineering Techniques

Modern-age cell phones come with contrasting features such as the battery, connectivity, storage, Bluetooth connection, and many more which play a vital role in determining its price. The main goal of this paper is to present a comparative study of various machine learning models which on analyzing and considering different characteristics of a cell phone would categorize the price range of the same. Our proposed study can be helpful for the sales and marketing industry in promoting cell phones based on their price and overcome the problems faced by the companies before the phone launch. Appropriate data preprocessing was done before training the eleven classifier models that are considered during the experiment which includes Artificial Neural Network (ANN), Support Vector Machine (SVM), etc. In our proposed work, we did a comparative study based on the performance metrics of all the models and classified phone models into four different categories namely low, medium, high, and very high cost. Among all the classifiers SVM achieved the highest accuracy of 96.77
^%
outperforming other models.