LLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion
When the competition in e-commerce rises, it is essential to ensure content is creative as well as effective in driving conversions. Using language generation from LLMs, we suggest a process that includes prompt engineering, multi-objective training and post-processing to make marketing texts engaging and effective for sales. We use a two-step process that applies sentiment modification, boosts diversity and adds calls to action. The way we test offline and online helps achieve a 12.5% increase in click through rate (CTR) and 8.3% increase in conversion rate (CVR). With this solution, creating texts can be automated and it will guide future improvements in live, customized user experiences.
Authors
- D. Wang
- Tianle Zhang
- Haotian Lyu (ORCID: https://orcid.org/0009-0005-3225-8676)
- Y. X. Zhao
- Huan Yang
Institutions
- University of Southern California (US)
- Duke University (US)
- Washington University in St. Louis (US)
- Oldham Council (GB)
- University of Houston (US)
Publication Details
- Published
- 2025-06-06
- DOI
- https://doi.org/10.1145/3757749.3757850
- Citations
- 6
- Primary Topic
- Big Data and Business Intelligence
- Type
- article
- Field-Weighted Citation Impact
- 13.70