[1U5-IS-2b] Machine learning

[1U5-IS-2b-05] Predicting CTR of Responsive Search Ads Using Handcrafted Features

〇Melvin Charles Ortua Dy¹ (1. OPT, Inc.)

[[Online, Regular]]

Keywords:Machine Learning, Feature Engineering, Advertising

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.