Paper Info
Title
SVM-Based Techniques for Predicting Cross-Functional Team Performance: Using Team Trust as a Predictor
Abstract
Due to the characteristics of cross-functional teams, trust is crucial for cross-functional teams to enhance performance. However, as a significant factor, trust had been neglected in previous team performance models. In this paper, we investigate whether trust can be used as a predictor of cross-functional team performance by proposing a prediction model. The inputs of the model are both team structural and contextual (SC) factors, and project process (PP) factors, which are two major sources that form team trust. The output of the model is different levels of team performance, which consists of internal performance and external performance. The support vector machine techniques are used to establish the model. Results show that prediction accuracy is high (84.95%) when using both SC and PP factors as inputs, while PP factors have better prediction accuracy than SC factors on team performance and internal performance. It is suggested that team trust can be used as a good predictor of cross-functional team performance. In practice, this paper presents a better understanding of the relationship between trust and performance in cross-functional teams, and thus, enhances practitioners' managerial skills. It also gives reference for managers to dynamically control and predict team performance during project period.
Year
DOI
Venue
2015
10.1109/TEM.2014.2380177
IEEE Trans. Engineering Management
Keywords
Field
DocType
Cross-functional team (CFTs), support vector machine (SVM), team performance (TP), trust
Kernel (linear algebra),Skills management,Project management process,Support vector machine,Knowledge management,Engineering,Cross-functional team
Journal
Volume
Issue
ISSN
62
1
0018-9391
Citations 
PageRank 
References 
1
0.35
9
Authors
2
Name
Order
Citations
PageRank
Lianying Zhang161.81
Xiang Zhang219534.67