Machine learning approach for predicting end price of online auction

An online auction is an auction held over the internet. In today's era of the internet, economies have changed the way than they were a few years back. The scope and reach of online auctions have been propelled by internet to the prominent level because online auctions break down and remove the physical limitations of traditional auctions such as geography, presence, time, space, etc. As online auction has become one of the fastest growing modes of online commerce transaction, sellers and buyers have started preferring to go online for purchasing and selling products respectively. As eBay has been the leading online auction marketplace for nearly two decades, the proposed system collected huge auction data from eBay and machine learning algorithms are used to predict end price of auction items. The proposed system is trained with 70% of dataset and 30% of dataset is used for testing. The proposed system used Naive Bayes which gives 99.33% accuracy in classification of whether the item will sell or not and kernel mapping SVM gives 96.3% accuracy for predicting whether an item maximize profit or not.