ChatGPT Referrals to E-Commerce Websites
Topics: LLMO / GEO, OpenAI / ChatGPT, Shopping
This study investigates the performance of Organic Large Language Model (OLLM) traffic, specifically from ChatGPT referrals, compared to traditional digital channels in e-commerce using one year of first-party data from 973 websites. Contrary to widespread expectations of LLM superiority, the analysis finds that OLLM traffic significantly underperforms all traditional channels, including Google’s organic and paid search, on key financial metrics like conversion rate (CR) and revenue per session (RPS), though it does outperform paid social media. While OLLM shows positive signs, such as a favorable bounce rate indicating relevance and an improvement in conversion rates over time, its overall trajectory, countered by a declining Average Order Value (AOV), suggests it is unlikely to displace traditional channels in the immediate future.
