Not all teleworkers reduce travel: An intensity-dependent behavioral framework with explainable machine learning

Abstract

Previous studies have yielded mixed findings on the relationship between teleworking and travel, possibly due to overlooking teleworking intensity and its evolving impacts. This study examines how teleworking is associated with overall vehicle miles traveled (VMT) and vehicle travel time (VTT) across a spectrum of intensities, measured by the number of remote-work days per week. Using travel survey data in the Puget Sound Region, Washington, we estimate four explainable machine learning models (XGBoost with SHAP) that incorporate behavioral, socio-demographic, and built-environmental characteristics. Results find an intensity-dependent relationship among typical workers. Low-intensity teleworking (1 day/week) is associated with increased travel both pre- and post-pandemic, while moderate teleworking (2 days/week) shows near-neutral or marginally positive associations. In contrast, regular teleworking (3–5 days/week) is correlated with reduced travel. In 2023, teleworking intensity ranks among the top six contributors, accounting for 6.84% and 4.08% of model explainability for VMT and VTT, respectively, higher than in 2017. The reductions scale with intensity. Holding other factors constant, high-frequency teleworkers (3 days/week) in 2023 accrued approximately 10 fewer miles and 3 fewer minutes per five-day workweek than fully on-site workers, whereas full teleworkers (5 days/week) saved 19 fewer miles and 23 fewer minutes. These impacts are concentrated among high-frequency teleworkers with longer commute distances, while the effects are mixed among shorter-distance commuters. Teleworking can moderate impacts of other factors, such as commute distance, income, and population density. These findings help reconcile prior inconsistencies, showing that teleworking's role depends on intensity rather than simple adoption.