What is it about?

Meetup helps people find local gatherings, but with so many events listed, it’s hard to spot the ones you’ll really enjoy. Our study introduces a simple recommendation system that looks at the events you’ve attended before and the topics you care about to suggest new meetups just for you. We tested it on data from 100,000 users and showed it reliably predicts events you’re likely to join. This makes discovering and attending the right events faster, more personal, and more fun for everyone.

Featured Image

Why is it important?

This work is the first to apply a tailored link‐prediction approach to Meetup’s event network, making event recommendations more accurate by combining users’ past attendance and personal interests. In an era of information overload, it delivers timely, personalized suggestions that help people discover the right local gatherings without endless browsing. By improving match accuracy, our method boosts event attendance and community engagement, offering organizers a practical tool to grow participation and attendees a more enjoyable, relevant experience.

Perspectives

Working on this project showed me firsthand how much potential lies in simple, user-centric approaches to recommendation. By focusing only on the two ingredients everyone already provides—what events they attended and what topics they care about—we achieved surprisingly strong prediction performance without needing complex social graphs or heavy profile data. Personally, I’m excited by how this minimal setup can be extended: imagine layering in real-time context (like time of day or location), social ties (friends’ RSVPs), or even mood signals from quick surveys. That blend of algorithmic simplicity and human factors makes our method both practical today and a springboard for richer, more dynamic event matchmaking tomorrow.

Dr. Ahmet Anıl Müngen
OSTIM Technical University

Read the Original

This page is a summary of: A Novel Method for Event Recommendation in Meetup, July 2017, ACM (Association for Computing Machinery),
DOI: 10.1145/3110025.3119397.
You can read the full text:

Read

Contributors

The following have contributed to this page