A Bayesian Network for Evaluating Software Project Team Fit: An Industrial Case Study

• Felipe Cunha UFCG http://orcid.org/0000-0001-6836-7560
• Mirko Perkusich UFCG https://orcid.org/0000-0002-9433-4962
• Danyllo Albuquerque UFCG https://orcid.org/0000-0001-5515-7812
• Kyller Gorgônio UFCG https://orcid.org/0000-0001-9796-1382
• Angelo Perkusich UFCG https://orcid.org/0000-0002-7377-1258

DOI: https://doi.org/10.5753/ise.2025.14877

Resumo

[Context] Forming effective software development teams requires balancing both technical and collaborative factors. While optimization methods—such as genetic algorithms—have been applied to automate team formation, they typically rely on fitness functions built from fixed weights or handcrafted rules. These ad hoc formulations rarely reflect structured expert reasoning and may misalign with organizational expectations. [Objective] This study focuses on constructing a Bayesian Network (BN) that formally encodes expert knowledge about team-project fit. The BN is intended to serve as a reusable, interpretable fitness function in future optimizationbased team formation systems. [Method] We conducted a case study in a large software organization with over 300 employees. Through expert workshops, we identified relevant developer capabilities, defined qualitative states, and structured the BN accordingly. Conditional Probability Tables (CPTs) were populated using expertlabeled what-if scenarios, then calibrated using the Ranked Nodes method. [Results] The final BN comprises nodes for technological and collaboration fit. Validation against held-out, expert-labeled scenarios yielded consistently low Brier Scores, demonstrating strong alignment with expert expectations. [Conclusion] BNs offer a viable, interpretable mechanism for encoding expert knowledge in team formation. This work establishes a structured and transparent foundation for future integration into automated team formation workflows.

Palavras-chave: Bayesian Networks, Software Team Formation, Software Engineering, Knowledge Engineering, Expert Systems

Referências

Alexandre Costa, Felipe Ramos, Mirko Perkusich, Emanuel Dantas, Ednaldo Dilorenzo, Ferdinandy Chagas, André Meireles, Danyllo Albuquerque, Luiz Silva, Hyggo Almeida, and Angelo Perkusich. 2020. Team Formation in Software Engineering: A Systematic Mapping Study. IEEE Access 8 (2020), 145687–145712. DOI: 10.1109/ACCESS.2020.3015017

Felipe Cunha, Mirko Perkusich, Danyllo Albuquerque, Kyller Gorgônio, Hyggo Almeida, and Angelo Perkusich. 2025. A Genetic Algorithm with Convex Combination Crossover for Software Team Formation: Integrating Technical and Collaboration Skills. In Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing. 146–153.

Felipe Cunha, Mirko Perkusich, Danyllo Albuquerque, Kyller Gorgônio, Hyggo Almeida, and Angelo Perkusich. 2025. TeamPlus: A data-driven tool utilizing a Genetic Algorithm for optimal software team formation. SoftwareX 30 (2025), 102174.

Norman Fenton and Martin Neil. 2018. Risk assessment and decision analysis with Bayesian networks. Crc Press.

Norman E Fenton, Martin Neil, and Jose Galan Caballero. 2007. Using ranked nodes to model qualitative judgments in Bayesian networks. IEEE transactions on knowledge and data engineering 19, 10 (2007), 1420–1432.

Arthur Freire, Manuel Neto, Mirko Perkusich, Alexandre Costa, Kyller Gorgónio, Hyggo Almeida, and Angelo Perkusich. 2022. A literature-based thematic network to provide a comprehensive understanding of agile teamwork (106). International Journal of Software Engineering and Knowledge Engineering 32, 05 (2022), 645–659.

Arthur Freire, Mirko Perkusich, Renata Saraiva, Hyggo Almeida, and Angelo Perkusich. 2018. A Bayesian networks-based approach to assess and improve the teamwork quality of agile teams. Information and Software Technology 100 (2018), 119–132.

Gleyser Guimarães, Icaro Costa, Mirko Perkusich, Emilia Mendes, Danilo Santos, Hyggo Almeida, and Angelo Perkusich. 2024. Investigating the relationship between personalities and agile team climate: A replicated study. Information and Software Technology 169 (2024), 107407.

Radin Hamidi Rad, Hossein Fani, Ebrahim Bagheri, Mehdi Kargar, Divesh Srivastava, and Jaroslaw Szlichta. 2023. A variational neural architecture for skill-based team formation. ACM Transactions on Information Systems 42, 1 (2023), 1–28.

Martin Hoegl and Hans Georg Gemuenden. 2001. Teamwork quality and the success of innovative projects: A theoretical concept and empirical evidence. Organization science 12, 4 (2001), 435–449.

Martí Manzano, Claudia Ayala, Cristina Gómez, Antonin Abherve, Xavier Franch, and Emilia Mendes. 2021. A method to estimate software strategic indicators in software development: an industrial application. Information and Software Technology 129 (2021), 106433.

George Marsicano, Fabio QB da Silva, Carolyn B Seaman, and Breno Giovanni Adaid-Castro. 2020. The Teamwork Process Antecedents (TPA) questionnaire: developing and validating a comprehensive measure for assessing antecedents of teamwork process quality. Empirical Software Engineering 25, 5 (2020), 3928–3976.

Emilia Mendes. 2014. Expert-based knowledge engineering of bayesian networks. In Practitioner’s Knowledge Representation: A Pathway to Improve Software Effort Estimation. Springer, 73–105.

Maziar Raissi, Zhicheng Wang, Michael S Triantafyllou, and George Em Karniadakis. 2019. Deep learning of vortex-induced vibrations. Journal of fluid mechanics 861 (2019), 119–137.

Silja Renooij and Cilia Witteman. 1999. Talking probabilities: communicating probabilistic information with words and numbers. International Journal of Approximate Reasoning 22, 3 (1999), 169–194.

Sai Datta Vishnubhotla and Emilia Mendes. 2024. Examining the effect of software professionals’ personality & additional capabilities on agile teams’ climate. Journal of Systems and Software 214 (2024), 112054.

Jared Willard, Xiaowei Jia, Shaoming Xu, Michael Steinbach, and Vipin Kumar. 2022. Integrating scientific knowledge with machine learning for engineering and environmental systems. Comput. Surveys 55, 4 (2022), 1–37.