Prediction of Smartphone Prices in the market using Machine Learning Algorithms: A Case Study

Smartphones and mobile devices have become a fundamental part in our modern world, transforming the way we communicate, work and access information. Their significance lies in providing access to a vast number of applications and services. Primarily, smartphones serve as a powerful communication tool enabling us to contact people across large geographical boundaries. With features such as calls, texts and various messaging apps, individuals can communicate easily. As technology continues to advance, predicting the prices of mobile phones becomes crucial for various stakeholders in the market. This is where Machine Learning (ML) techniques have a key role. Regression and Classification methods are important components of these techniques, each serving a different and distinct purpose. In this study we apply Regression methods such as SVR and LSTM as well as Classification methods such as K-Means, KNN, Naïve Bayes, Decision Tree, Random Forest, and Gradient Boosting to categorize data in predefined classes. Comparison of each ML technique finally conclude which gives the most accurate prediction. Smartphones and mobiles play a pivotal role in the interconnected world, impacting information access and productivity. Predicting the prices of mobile phones through Machine Learning techniques is essential for making informed decisions in a dynamic market. This study can provide tools necessary to anticipate future trends, benefiting consumers, manufacturers and investors alike.