Inbound business activities and industrial linkages: insights from Shanghai using a big–small data integration framework

Abstract Intercity business travel is a critical yet poorly observed channel through which global cities sustain functional linkages. Existing studies often infer ties from firm networks or use purpose-agnostic mobility flows, leaving the behavioral and industrial logic of intercity connectivity underexplained. We develop a transferable big-small data framework to identify intercity business travelers and to examine industrial-structure associations in intercity exchanges. Using Shanghai as a case, behavioral signatures from a travel survey are used to train a purpose-inference model, which is then transferred to large-scale mobile phone data to classify inbound business flows. We then relate inbound business intensity to industrial similarity and characterize nonlinear associations and cross-sector interaction patterns using interpretable machine-learning analysis. Results show that business travelers constitute 36.9% of short-term visitors and their destinations reinforce Shanghai’s polycentric structure. Industrial similarity exhibits a U-shaped statistical association with inbound business flows, with predicted flows reaching their lowest level at intermediate similarity and increasing at both higher and lower observed similarity levels. Cross-industry pairs account for a larger share of the modeled interaction intensity, with advanced producer services frequently appearing in the industrial configurations associated with inbound business flows. These findings deepen our understanding of the dynamics of intercity business travel and provide insights into regional planning and the governance of metropolitan services.