OKG: On-the-Fly Keyword Generation in Sponsored Search Advertising

TL;DR

This paper introduces OKG, a real-time keyword generation method using LLMs for sponsored search advertising, which adapts dynamically to KPI changes, improving responsiveness over static datasets.

Contribution

The paper presents the first real-time keyword generation approach with an accompanying public dataset, enhancing adaptability in sponsored search advertising.

Findings

OKG significantly improves keyword responsiveness and adaptability.

The dataset enables future research in dynamic keyword generation.

Experimental results outperform traditional static methods.

Abstract

Current keyword decision-making in sponsored search advertising relies on large, static datasets, limiting the ability to automatically set up keywords and adapt to real-time KPI metrics and product updates that are essential for effective advertising. In this paper, we propose On-the-fly Keyword Generation (OKG), an LLM agent-based method that dynamically monitors KPI changes and adapts keyword generation in real time, aligning with strategies recommended by advertising platforms. Additionally, we introduce the first publicly accessible dataset containing real keyword data along with its KPIs across diverse domains, providing a valuable resource for future research. Experimental results show that OKG significantly improves keyword adaptability and responsiveness compared to traditional methods. The code for OKG and the dataset are available at https://github.com/sony/okg.