Abstract:
Machine learning-based classification techniques help to solve the problem related to
decision making. In many areas of price, prediction is used like housing price prediction,
stock price prediction different classification algorithms used. Some of them are used
artificial neural networks. In this study, three different classification techniques used for
predicting the mobile price range. The first one is Naïve Bayes second one is Decision Tree
and the third one is the Random Forest machine learning algorithm. The accuracy got my first two
techniques respectively 83% and 84%. As the accuracy of Naïve Bayes is lower than
the decision tree so Naïve Bayes is not considered. So, for improving the accuracy of the Decision
Tree, the parameter has been pruned and later Random Forest has been used. It gives 90%
accuracy for this dataset. And also, performance evaluation is performed for Decision Tree
and Random forest like Precision, Recall.
