Game Bear
Machine-learning prediction of long-term ad conversion
Game Bear raised its overall ad conversion rate by 20% to 30% by predicting which ads would convert
Problem
Game Bear, a Hong Kong mobile game developer, needed to know which of its ads would deliver conversions over the long term. Waiting for full results meant spending on ads that did not perform.
Approach
Game Bear uses Vertex AI to predict an ad's long-term conversion rate from its performance in the first two to three days after release. The team uses the predictions as a reference and distributes only the ads that are expected to convert better. The company plans to extend AI to game features, including AI-powered non-player characters.
Results
Takeaway
Game Bear judges ads on a few days of early data instead of waiting for full results. The company did not say how it measured the conversion gain.
Categories
- Size
- Small business
- Industry
- Media and entertainment
- Business function
- Marketing and sales
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Vendor case study
Sources
Source summaries
Google Cloud's customer story describes how the Hong Kong game developer Game Bear uses Vertex AI to predict long-term ad conversion from the first days of ad performance. It reports a 20% to 30% rise in overall ad conversion rate; the rest of the page covers networking and analytics. The page carries no date; the Internet Archive first saved it on May 7, 2024.
Full details are in the original sources.