Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Time diagram of a player’s play log data.

The player has played n = 8 times. The first three plays occurred within two days of the first play. The next two plays occurred in the following two days.

More »

Fig 1 Expand

Fig 2.

Two churners and two active users.

Each row describes play log records of a user, and a user with no play log record in the churn prediction period is defined as a churner. When desired, a larger CP can be chosen for defining churn.

More »

Fig 2 Expand

Table 1.

Three games and their data.

More »

Table 1 Expand

Table 2.

Principal attributes of Game #1.

More »

Table 2 Expand

Table 3.

Principal attributes of Game #2.

More »

Table 3 Expand

Table 4.

Principal attributes of Game #3.

More »

Table 4 Expand

Table 5.

Common features of the three games.

More »

Table 5 Expand

Table 6.

Game-specific features of Game #2 and Game #3.

More »

Table 6 Expand

Fig 3.

Evaluation of single features.

(a) Based on correlation with churn. (b) Based on gradient boosting performance.

More »

Fig 3 Expand

Table 7.

Overall average rankings for single features.

More »

Table 7 Expand

Table 8.

Feature combination result.

The underlined features are the top 2 from the single-feature ranking.

More »

Table 8 Expand

Fig 4.

AUC vs. number of utilized features.

Increasing number of features has only a marginal effect on AUC performance, especially after 2~3 features are included.

More »

Fig 4 Expand

Fig 5.

Input to the deep learning algorithms.

For each user, the value in each time frame is the sum of all scores that were recorded during the time frame.

More »

Fig 5 Expand

Table 9.

Performance (AUC) comparison of three conventional algorithms and two deep learning algorithms (OP = 5 days, CP = 10 days).

More »

Table 9 Expand

Fig 6.

AUC performance as a function of OP and CP selections. The churn prediction performance is improved by increasing number of observation days and by decreasing number of churn prediction days.

(a)(c)(e) AUC vs. (OP,CP) for Game #1, #2, and #3, respectively (b)(d)(f) AUC vs. CP for four fixed OP values for Game #1, #2, and #3, respectively.

More »

Fig 6 Expand