Player Time Band Classification for Game Completion Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting game objective completion times in video games are inaccurate, as they rely on average completion times, which fail to account for individual player variability and gameplay styles, leading to significant prediction errors.
Innovation Solution
A system using linear regression and conditional inference trees to classify players into time bands based on their historical quest completion speeds, providing more accurate predictions by analyzing decile scores and normalizing completion times across players.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If average completion times are used for all players, then the prediction method is simple, but the prediction accuracy is low
Solution Approach 1:
The player population is segmented into different time bands (fast, medium, slow) based on their completion speed decile scores. Each time band has its own prediction model trained on relevant historical data, allowing accurate predictions tailored to individual player characteristics rather than using a single average for all players.
2Measurement precision
If player classification into time bands is implemented, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
Player classification into time bands is performed in advance based on historical completion data and decile scores. The conditional inference tree model pre-processes player characteristics and assigns players to appropriate time bands before prediction is needed. This preliminary classification enables accurate predictions without requiring complex real-time analysis during gameplay.
3Measurement precision
If individual player variability is accounted for, then prediction accuracy improves, but data processing requirements increase
Solution Approach 1:
The system extracts key characteristics from player data, specifically the completion speed decile score, which captures individual player variability in a single normalized metric. This extracted feature is then used by the conditional inference tree to classify players into time bands, reducing the need to process and store extensive raw gameplay data while maintaining high prediction accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of predicting a game objective completion time for a particular game objective for a particular user comprises; for a corpus of other users who have completed the particular game objective, determining a plurality of game objective completion time deciles for a preceding predetermined number of other game objectives completed by users in the corpus of users, deriving a representative completion time decile from the plurality of game objective completion time deciles for each user in the corpus of users, and generating a time band classification using the representative decile values as input variables and corresponding game objective completion times for the particular game objective as the output variable; for the particular user, determining a game objective completion time decile for the preceding predetermined number of other game objectives completed by the particular user, deriving a representative completion time decile from the plurality of game objective completion time deciles for the particular user, and identifying a time band classification of the particular user using the representative completion time decile for the particular user as input to the generated time band classification; and outputting predicted game objective completion time data for the particular game objective for the particular user based upon the identified time band classification.