Get 20M+ Full-Text Papers For Less Than $1.50/day. Subscribe now for You or Your Team.

Learn More →

Data Engineering and Communication TechnologyPrediction of Phone Prices Using Machine Learning Techniques

Data Engineering and Communication Technology: Prediction of Phone Prices Using Machine Learning... [In this modern era, smartphones are an integral part of the lives of human beings. When a smartphone is purchased, many factors like the display, processor, memory, camera, thickness, battery, connectivity and others are taken into account. One factor that people do not consider is whether the product is worth the cost. As there are no resources to cross-validate the price, people fail in taking the correct decision. This paper looks to solve the problem by taking the historical data pertaining to the key features of smartphones along with its cost and develop a model that will predict the approximate price of the new smartphone with a reasonable accuracy. The data set [12] used for this purpose has taken into consideration 21 different parameters for predicting the price of the phone. Random forest classifier, support vector machine and logistic regression have been used primarily. Based on the accuracy, the appropriate algorithm has been used to predict the prices of the smartphone. This not only helps the customers decide the right phone to purchase, it also helps the owners decide what should be the appropriate pricing of the phone for the features that they offer. This idea of predicting the price will help the people make informed choice when they are purchasing a phone in the future. Among the three classifiers chosen, logistic regression and support vector machine had the highest accuracy of 81%. Further, logistic regression was used to predict the prices of the phone.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Data Engineering and Communication TechnologyPrediction of Phone Prices Using Machine Learning Techniques

Part of the Advances in Intelligent Systems and Computing Book Series (volume 1079)
Editors: Raju, K. Srujan; Senkerik, Roman; Lanka, Satya Prasad; Rajagopal, V.

Loading next page...
 
/lp/springer-journals/data-engineering-and-communication-technology-prediction-of-phone-v0wnpgH7GK

References (10)

Publisher
Springer Singapore
Copyright
© Springer Nature Singapore Pte Ltd. 2020
ISBN
978-981-15-1096-0
Pages
781 –789
DOI
10.1007/978-981-15-1097-7_65
Publisher site
See Chapter on Publisher Site

Abstract

[In this modern era, smartphones are an integral part of the lives of human beings. When a smartphone is purchased, many factors like the display, processor, memory, camera, thickness, battery, connectivity and others are taken into account. One factor that people do not consider is whether the product is worth the cost. As there are no resources to cross-validate the price, people fail in taking the correct decision. This paper looks to solve the problem by taking the historical data pertaining to the key features of smartphones along with its cost and develop a model that will predict the approximate price of the new smartphone with a reasonable accuracy. The data set [12] used for this purpose has taken into consideration 21 different parameters for predicting the price of the phone. Random forest classifier, support vector machine and logistic regression have been used primarily. Based on the accuracy, the appropriate algorithm has been used to predict the prices of the smartphone. This not only helps the customers decide the right phone to purchase, it also helps the owners decide what should be the appropriate pricing of the phone for the features that they offer. This idea of predicting the price will help the people make informed choice when they are purchasing a phone in the future. Among the three classifiers chosen, logistic regression and support vector machine had the highest accuracy of 81%. Further, logistic regression was used to predict the prices of the phone.]

Published: Jan 9, 2020

Keywords: Support vector machine; Logistics regression; Smartphone prices; Random forest

There are no references for this article.