A Machine Learning Approach to Combining Individual Strength and Team Features for Team Recommendation

Liu, Haibin; Qiao, Mu; Greenia, Daniel; Akkiraju, Rama; Dill, Stephen; Nakamura, Taiga; Song, Yang; Nezhad, Hamid Motahari

doi:10.1109/icmla.2014.39

Cited by 11 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm's ability to balance diverse skills and personalities could promote synergistic collaboration, as was also concluded in the study by Berktaş and Yaman [41]. This could enhance project success rates and improve overall organizational productivity, much like the methods suggested by Liu et al [54] and Fatahi and Lorestani [55]. Our model can also be applied in online collaborative platforms.…”

Section: Discussionsupporting

confidence: 59%

“…Notably, more advanced methods such as genetic algorithms (GAs) have been utilized to optimize multiple team attributes like skills, preferences, and demographics [48][49][50][51][52]. Similarly, machine learning techniques have been used to suggest optimal team configurations based on individual attributes [53,54], and expert systems [55,56] have employed rules and heuristics based on domain knowledge to assist in team formation. However, these methods still face challenges, especially in scalability, robustness, and accommodating the complex nature of the problem, including factors like individual skillsets, potential for collaboration, and various constraints.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging Multi-Criteria Integer Programming Optimization for Effective Team Formation

Singh,

Huynh,

Nguyen

et al. 2023

Preprint

View full text Add to dashboard Cite

The research addresses a critical aspect of organizational settings – team formation – which is vital for effective team-based learning. In many organizational environments, successful teamwork depends on the composition of teams that consider various criteria, such as skill levels, background, and personality traits. Meanwhile, maintaining fairness and equity among teams is crucial to ensure equal opportunities for all team members. Our research framework lies in its ability to model a diverse range of factors, while simultaneously maximizing within-team diversity and minimizing conflict levels. In this study, we introduce a novel application of multi-criteria integer programming (MCIP) that diverges from traditional and single-objective optimization methods to address the complexity of team formation with a focus on multiple criteria. This approach offers a comprehensive solution that accommodates multiple criteria simultaneously. The contributions of this paper are: 1) An innovative optimization model for team formation that addresses the complex task of maximizing intra-group diversity while minimizing inter-group diversity. 2) Addressing the challenge of forming balanced and diverse student teams and providing educators with a practical tool for effective team formation.

show abstract

Section: Discussionsupporting

confidence: 59%