According to China Times, Visa launched its first AI shopping evaluation standard on November 13, with initial testing showing a 43.4% failure rate across 22 AI models from 12 research teams. The evaluation assessed AI models' performance in 15 real-world shopping scenarios including television, laptop, and personal care appliances purchases. Top-performing models achieved an 82.2% pass rate, while the lowest reached only 28.9%, with just 33% of models passing all three tests across all scenarios. Visa found that deeper understanding of consumer needs directly correlates with better performance: models that gathered the most purchase intent information averaged 68% pass rates, compared to 44.4% for models with minimal customer insight. The company plans to expand the evaluation benchmark with additional shopping scenarios and extend testing to checkout and payment stages.
Disclaimer: This content is for informational purposes only and does not constitute investment advice or encourage the buying or selling of crypto assets. It is intended to provide information about industry developments and is not directly related to the services offered by Gate TR. Although information obtained from third-party sources has been carefully reviewed, Gate TR assumes no responsibility for any errors or omissions. Crypto assets involve high risks and may experience significant price fluctuations. Before making any investment decisions, you should assess your financial situation and risk tolerance, conduct your own research, and make decisions independently.
