.png){kind=icon}
.png){kind=icon}
Return
Predicting digital product performance with team composition features derived from a graph network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.dss.2024.114266.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper examines video games, a form of digital innovation, and seeks to predict a successful game based on the composition of game development team members. Team composition is measured with observable features generated from a graph network based on development team information derived from individual team member work on previous games. Features include network features, such as team member closeness, success percentile, and failure percentile, and non-network features, such as the number of games published prior by the studio. We propose a novel framework using these features to predict the chance of success for new games with an accuracy higher than 92%. Further, we investigate important features for prediction and provide model interpretability for practical implementations. We then build a decision support tool that allows video game producers, and associated stakeholders such as investors, to understand how the predictive model decides, predicts, and performs its recommendations. The findings have implications for those seeking to proactively impact digital product performance through graph network-generated features of team composition, where features are directly observable, as opposed to features that are more challenging to observe, such as personalities.
Keywords:
Digital innovation
Digital product performance
Machine learning
Model interpretability
Team composition decision making
Observable network features
Journal
IF:
6.8
Papers:
3.8K
Citations:
1.5W