GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of GDC sessions by time, pass type, topic, and format. With GDC Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App, once live.

If you've registered for GDC, you can use the same login credentials for your Session Scheduler account. Adding a session to your schedule does not guarantee you a seat. Sessions do fill up, so please arrive early to sessions that you would like to attend.

AI Summit: The AI Knows You Better Than Yourself: Mining Player Pursuits in Justice Online

Renjie Li (Head of AI, NetEase)

Location: Room 2002, West Hall

Date: Monday, March 16

Time: 4:40pm - 5:10pm

Pass Type: All Access Pass, Core+Summits Pass, Summits Pass - Get your pass now!

Topic: Programming

Format: Session

Vault Recording: TBD

Audience Level: Intermediate

The AI knows you better than yourself! In MMORPGs, millions of players join together to enjoy a living and breathing virtual world. Every player has several attributes, like online time, game currency, game scores, etc. Players participate in various social interactions, like making friends, trading assets, sending messages, forming teams, etc. Mining player pursuits facilitates the personalized services in Justice Online, which is one of the most successful MMORPG in China. Time series prediction and link weight prediction are the two main analyses in player pursuits mining. They are affected by many complex factors, including temporal characteristics, social characteristics, collaborative characteristics, task characteristics, and the intrinsic causality between them. To tackle these challenges, this talk will show you how NetEase Fuxi AI Lab makes their AI model better and better, achieving great performance improvements. More examples and applications about how they use the mining results will also be given, such as churn prediction, return prediction, real money trading detection, consumption prediction, recharge prediction, player ability guide, team formation, friendship suggestion, and chat fast entry. Open source code and open dataset demos will be provided.


The attendees will learn how artificial intelligence technologies can be applied to the in-game player related data to make time series prediction and link weight prediction in order to help mining player pursuits better in online games.

Intended Audience

The presentation is for the game operation professionals who want to apply artificial intelligence techniques to help mining player pursuits in online games. The game designers and game developers will benefit as well. The speakers will use some math lingo, but keep it to a minimum.