Effective matchmaking in online multiplayer games is essential for ensuring balanced competition and player satisfaction. Traditional rating systems primarily assess individual skill but overlook social and coordination-based factors that influence team performance. In this study, we adapt the team player effect (TPE)—a metric derived from residual-based estimation—to quantify a player's consistent ability to enhance team performance beyond their technical skill. Originally studied in economics and organizational science, the TPE captures systematic contributions to teamwork that extend beyond task proficiency. Using a large-scale dataset from Age of Empires II: Definitive Edition, we demonstrate that incorporating TPE and team familiarity significantly improves match outcome prediction compared to Elo-based benchmarks. Our results indicate that the importance of TPE increases with team size, suggesting its relevance in facilitating coordination in larger teams. Our findings suggest that accounting for TPE can enhance the fairness and competitiveness of team-based matchmaking across various game environments.

Effective teamwork is essential in structured, performance-driven environments, from professional organizations to high-stakes competitions. As tasks grow more complex, high performance requires not only technical proficiency but also interpersonal skills that enable effective coordination. Prior research has identified social skills and familiarity as key drivers of team performance, but their combined effects—particularly in temporary teams—remain underexplored due to data and design limitations. We analyze a large panel dataset of temporary teams in a competitive environment. The data capture millions of interactions in the real-time strategy game Age of Empires 2, where players are assigned quasi-randomly to teams and must coordinate under pressure. We isolate individual contributions to team success by comparing observed outcomes to predictions based on task proficiency. Our findings confirm a robust "team player effect": certain individuals consistently improve team outcomes beyond what their technical skills predict. This effect is amplified by team familiarity—teams with shared experience benefit more from the presence of such individuals. The effect also grows with team size, suggesting that social skills help overcome coordination challenges in larger groups. These results demonstrate the team player effect's robustness in a quasi-randomized, high-stakes setting. Social skills and familiarity interact complementarily—not additively—offering broader implications for team-based production in organizations and labor markets.

We introduce the logarithmic stochastic tracing procedure, a homotopy method to compute stationary equilibria for finite and discounted stochastic games. We build on the linear stochastic tracing procedure but introduce logarithmic penalty terms as a regularization device, which brings two major improvements. First, the scope of the method is extended: it now has a convergence guarantee for all games of this class rather than just generic ones. Second, by ensuring a smooth and interior solution path, computational performance is increased significantly. A ready-to-use implementation is publicly available. As demonstrated here, its speed compares quite favorably to other available algorithms, and it allows us to solve games of considerable size in reasonable times. Because the method involves the gradual transformation of a prior into equilibrium strategies, it is possible to search the prior space and uncover potentially multiple equilibria and their respective basins of attraction. This also connects the method to established theory of equilibrium selection. History: Accepted by Antonio Frangioni, Area Editor for Design & Analysis of Algorithms – Continuous. Supplemental Material: The online appendix is available at https://doi.org/10.1287/ijoc.2022.0360 .