Predicting CTR of Responsive Search Ads Using Handcrafted Features

抄録

In this paper, I demonstrate that a reasonably sized set of handcrafted features (866, applied to titles and description texts separately) plus encoded metadata can be used to predict the click-through rates of the dynamic Responsive Search Ad format, exceeding the performance of some fine-tuned Transformer-based large language models at a fraction of the training cost.