Utilizing Players' Playtime Records for Churn Prediction: Mining Playtime Regularity

TL;DR

This paper proposes new universal features derived from players' playtime data to improve long-term player churn prediction in online games, aiming to help game operators retain players more effectively.

Contribution

It introduces novel playtime-based features specifically designed for long-term players to enhance churn prediction accuracy.

Findings

New playtime features improve churn prediction performance.

Features effectively identify players at risk of churning.

Method applicable to various online games.

Abstract

In the free online game industry, churn prediction is an important research topic. Reducing the churn rate of a game significantly helps with the success of the game. Churn prediction helps a game operator identify possible churning players and keep them engaged in the game via appropriate operational strategies, marketing strategies, and/or incentives. Playtime related features are some of the widely used universal features for most churn prediction models. In this paper, we consider developing new universal features for churn predictions for long-term players based on players' playtime.