The AI system works by analyzing hundreds of factors, including the reservation's proximity to the user's birthday, the user's age, length of stay, the listing's proximity to where the user is based, how far in advance the reservation is being made, and the type of listing. The system assigns every reservation a party risk, and depending on the risk tolerance that Airbnb has assigned for that country or area, the reservation will either be banned or greenlit. The company has also introduced "heightened party defenses" for holiday weekends. The system has been evaluated by Airbnb's anti-discrimination team to ensure fairness and accuracy.
Key takeaways:
- Naba Banerjee is in charge of Airbnb's worldwide ban on parties and has developed an anti-party AI system to halt high-risk reservations.
- The AI system looks at hundreds of factors, including the reservation's closeness to the user's birthday, the user's age, length of stay, the listing's proximity to where the user is based, and more.
- Since the worldwide launch of Banerjee's system in May, more than 320,000 guests have been blocked or redirected from booking attempts on Airbnb.
- Airbnb's party problem is complex and constantly evolving, requiring continuous monitoring and updating of the AI system to keep up with new ways users try to circumvent the system.