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.

Use the GDC 2021 Session Viewer to browse and sort the ever-growing list of sessions by day, time, pass type, topic, and format. All registered attendees will be able to build their personal schedule directly within the event platform, once live early July 2021. All times are listed in Pacific Time.

Multi-Model Approach to Hyper-Personalizing Your Game (Presented by TENTUPLAY)

Hyeyon Kwon  (CEO, TENTUPLAY)

Date: Thursday, July 22

Time: 9:40am - 10:10am

Pass Type: All Access Pass, Core Pass, Summits Pass, Expo Pass, Audio Pass, Independent Games Summit Pass

Topic: Business & Marketing

Format: Sponsored Session

Vault Recording: Not Recorded


People play game with different motives and expectations. Yet, game developers tend to rely on a single predictive model to segment and understand their players. TENTUPLAY breaks from the norm by building multiple empirically proven models that each correspondingly map distinct behavioral tendencies of players. Such approach overhauls existing drawbacks in single modeling paradigm by yielding adaptive and comprehensive player analytics. Multi-model analysis systematically identifies the most suitable models to employ for each game genre and its lifecycle stage. The models then analyze player behavior throughout their journey from D1 to synthetically reveal the reasoning behind their churn and purchase. Understanding these individual retention and consumption behavior is integral to leveraging further engagement with hyper-personalizing gaming experience for each player. This session dives deeper into the evidence of multi-model’s advantage and how it is substantively implemented to encourage more purchase and longer play time.


Multi-model analysis sheds light on how each player would behave differently based on their intrinsic needs and wants. Game developers can leverage this knowledge as to realize data-driven personalization. By individually encouraging purchase from the non-spending 99%, while ensuring longer play time, we hope our session helps game developers build a sustainable and profitable game.

Intended Audience

Game developers who are looking to improve LTV from effectively increasing player satisfaction and preventing churn will significantly benefit from this session. If your purpose is to create a data-driven game that requires a more in-depth understanding of the motives behind player churn and purchase, we highly encourage you to join us in this session.