This study examines Booking.com’s January 2025 update to its review scoring system, which shifts from an arithmetic mean of all guest reviews over the past 3 years to a weighted algorithm. The new system prioritizes recent reviews while reducing the impact of older ones. Using a sample of 100 Spanish hotels and 74,882 reviews, we identify the weighting scheme: 85% for reviews from the last 12-month period, 10% for previous year, and 5% for the year before that. Our findings indicate a minimal overall impact on hotel ratings, with most properties undergoing a variation of less than 0.1 points out of 10. While the updated system provides a more dynamic reflection of current service quality, it also introduces risks, such as increased vulnerability to fraudulent reviews and short-term fluctuations. This change poses challenges for academic studies on hotel reputation and highlights the need for greater transparency in algorithmic scoring systems.
No takes yet. Share an insight, caveat, or question.
Mellinas et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: