Risk-Aware Skill-Coverage Hybrid Workforce Configuration on Social Networks
New AI model solves NP-hard problem of balancing office safety with collaboration needs.
A research team led by Hui-Ju Hung has introduced a novel algorithmic framework to tackle one of the most pressing operational challenges of the post-pandemic era: optimally configuring hybrid workforces. Their paper, "Risk-Aware Skill-Coverage Hybrid Workforce Configuration on Social Networks," formulates the RSHWC problem, which models a company as a two-layer social network. This model simultaneously accounts for physical contact risks (like disease transmission) and social collaboration benefits, aiming to meet specific skill requirements while minimizing health hazards. The researchers formally proved this optimization problem is NP-hard, meaning finding the perfect solution is computationally intractable for large organizations, necessitating smart algorithmic approximations.
The team's answer is the Guided Risk-aware Iterative Assembling (GRIA) algorithm, a multi-stage solution that constructs a workforce, refines it to preserve critical skills, and replaces members to reduce risk. Tested on four real-world network datasets, GRIA consistently outperformed state-of-the-art baseline methods across various parameter settings. This work, accepted at the PAKDD 2026 conference, provides a rigorous, data-driven foundation for office re-entry policies, moving beyond guesswork to a model that quantifies the trade-off between collaboration efficiency and employee safety. It represents a significant step toward using computational social network analysis for practical, large-scale human resource planning.
- Proposes the RSHWC problem, an NP-hard challenge balancing onsite collaboration benefits against contact-based health risks.
- Introduces the GRIA algorithm, a 3-stage method that outperforms baselines on four real-world network datasets.
- Provides a formal model for companies to make data-driven hybrid work decisions based on skill graphs and contact networks.
Why It Matters
Offers a scalable, algorithmic solution for companies to design safer, more effective hybrid work policies based on data.