A 2020 perspective on “Online ad effectiveness evaluation with a two-stage method using a Gaussian filter and decision tree approach”

摘要

Online ads create opportunities for advisers to discover potential customers by delivering marketing massages through the Internet. Effectiveness evaluation of online ads is useful so they can save unnecessary costs and increase their profitability. The task of early removal of ineffective online ads is a key aspect of effectiveness evaluation. Few studies have focused on early removal of ineffective online ads though. To address this problem, we propose a two-stage method based on a Gaussian filter and a decision tree (M-GFDT). Our method uses a Gaussian filter to adjust distribution of business data in the first stage and builds a decision tree classifier to remove ineffective online ads and at the same time achieve high accuracy for predicting effective online ads. The second stage involves validation of our method experimentally, with data from a cross-border e-commerce firm. The research evaluation results demonstrate that our method is able to achieve high accuracy in predicting effective online ads. It also aids in the removal of ineffective online ads as early as possible. The prediction results of M-GFDT and the method itself are useful for helping advertisers to optimize their ad strategies.