Cornell researchers have developed a fairer system for search recommendations–from hotels to jobs to videos–so a few top hits don’t get all the exposure.
The new system provides more relevant options but distributes users’ attention more evenly across search results. It can be applied to online markets such as travel sites, hiring platforms and news aggregators.
Yuta Saito, a doctoral student in the field of computer science and Thorsten Joachims, professor of computer science and information science in the Cornell Ann S. Bowers College of Computing and Information Science, described their new system in “Fair Ranking as Fair Division: Impact-Based Individual Fairness in Ranking,” published in the Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
“In recommender systems and search engines, whoever gets ranked high draws a lot of benefit from that,” Joachims said. “The user’s attention can only be used in a limited way, so we must distribute it equally among the items. “
Conventional recommender systems attempt to rank items purely according to what users want to see, but many items receive unfairly low spots in the order. It is possible for items with similar merit to end up in different rankings. For some items, the chances of them being discovered on a platform can be worse than random chance.
To fix this problem, Saito created an improved ranking system that was based on economic principles. Joachims and Saito demonstrated the viability of the ranking system with real-world and synthetic data. Saito stated that fairness in ranking was completely redefined. It can be used for any type of two-sided rank system.
If used on YouTube, for instance, the recommender system will present a wider range of videos and potentially distribute earnings more evenly to content creators. “We want to satisfy the users of the platform, of course, but we should also be fair to the video creators, to sustain their long-term diversity,” Saito said.
In online hiring platforms, the fairer system would diversify the search results, instead of showing the same top candidates to all employers.
Additionally, the researchers point out that this type of recommender system could also help viewers discover new movies to watch online, enable scientists to find relevant presentations at conferences and provide a more balanced selection of news stories to consumers.
Algorithm increases fairness in search results
Team creates a fair ranking system to diversify search results (2022, September 19).
Retrieved 20 September 2022
Copyright is reserved for this document. Except for fair dealings for private study or research purposes, there is no
Part may not be reproduced without written permission. This content is only for informational purposes.