MLP modeling for search advertising price prediction

Abstract

As the use of online and various smart devices spread, the use of online search engines became more active. As Internet shopping has evolved through online search engines, competition is under way to launch its link at the top of search engines to expose its links to prospective shoppers. This trend has contributed to the increase in advertising costs in the search advertising market. In this case, the value of the search keyword is generally calculated based on the frequency of the search keyword, however the search engine configures the price of the search keyword through the private auction method without disclosing the price in real time. Finally, it is difficult to reach the exact price and position by passive statistical method in order to predict the price of the search keyword. There is a growing demand for automation methodologies to perform this process quickly and efficiently. In this paper, we propose a Multi-Layer Perceptron (MLP) Neural Network modeling method that estimates bid prices of search keywords by collecting search keywords. MLP is used because it uses generalized delta learning rules and easily gets trained in less number of iterations. In this paper, we propose a MLP based prediction modeling to predict optimal bidding price of the keyword in a specific ranking of search engine.