Online advertising has become lucrative for businesses to reach millions of customers. Revenue model for online advertising is different from conventional practice, as advertisers get charged only when users click on their advertisement; this method is referred as “pay-per-click”. Several studies have been carried using multi-criteria regression and kernel prediction algorithms to analyse click patterns. User profile and purchase history helps to identify the ad content to be displayed and the order in which they are displayed. Click-through rating method increases the probability of user watching and clicking on each ad. In the current study, we present a novel approach to improve the accuracy of the frequently clicked advertisements by using firefly algorithm. We have used KDD Cup 2012 datasets collected from popular websites selling US and UK products. The results of our study show 0.99 accuracy confirming our approach to be better than existing methods.
CITATION STYLE
Madhu Sudana Rao, N., Eranki, K. L. N., Harika, D. L., Kavya Sree, H., Sai Prudhvi, M. M., & Rajasekar Reddy, M. (2020). Optimization of Click-Through Rate Prediction of an Advertisement. In Advances in Intelligent Systems and Computing (Vol. 1087, pp. 579–589). Springer. https://doi.org/10.1007/978-981-15-1286-5_50
Mendeley helps you to discover research relevant for your work.