OKG: On-the-Fly Keyword Generation in Sponsored Search Advertising
This work addresses the need for real-time keyword adaptation in advertising for marketers, though it is incremental as it builds on existing LLM and advertising platform strategies.
The paper tackles the problem of static keyword datasets in sponsored search advertising by proposing OKG, an LLM agent-based method that dynamically generates keywords in real time based on KPI changes, resulting in significant improvements in adaptability and responsiveness compared to traditional methods.
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.