Strategic Business Models and Ecosystem Innovation: Integrating Graph & Network Algorithms with HR Analytics for Sustainable Talent Mobility and Workforce Location Planning

This study develops an integrated graph- and network-based HR analytics framework for sustainable talent mobility, workforce location planning, and ecosystem innovation. It improves talent-role matching while addressing diversity, environmental sustainability, and SDG 8 objectives.

A Design Science Research approach was adopted to develop and evaluate the model. Employees, roles, and locations are represented as interconnected nodes, with weighted edges capturing skill alignment, mobility costs, and diversity. Dijkstra’s shortest-path, Louvain community detection, max flow–min cut, and Node2Vec are integrated with ESG-constrained multi-objective optimization. SPSS was used for descriptive, reliability, and factor analyses.

The model was tested using a structured dataset of 500 workers covering skills, diversity, performance, and mobility expenses.

Skill fit improved by 30.6%, career-path length decreased by 25%, relocation carbon emissions declined by 33.5%, gender-diversity inequality reduced by 31.7%, high-potential retention increased from 68% to 87%, and SDG 8 alignment improved by 35.2%.

The study uniquely integrates graph algorithms, AI-based embeddings, HR analytics, optimization, and ESG constraints into a unified workforce-planning framework, enabling scalable, data-driven, equitable, and sustainable talent management.