Skills-approximate occupations: using networks to guide jobs retraining

Abstract

An issue often confronting economic development agencies is how to minimize unemployment due to disruptions like technological change, trade wars, recessions, or other economic shocks. Decision makers are left to craft policies that can absorb surplus labor with as little pain to workers as possible. The questions they face include how to re-employ displaced workers and how to fill labor shortages. To address such questions, we quantify the proximity of any two occupations based on the skills inherent in each. Taking labor skills as nodes, we model US labor as a weighted network of interdependent skills, deriving link values from geographical patterns of skill co-occurrence. We use this network to locate occupations, measure their proximity to each other, and identify which missing skills may inhibit workers from easily transitioning from one occupation to another. Thus, given that an occupation is a bundle of skills, we use our skills network to help policy makers identify which other occupations are most proximate a worker's current occupation. Finally, we apply our method to assess various worker retraining pathways for metropolitan Washington, DC, USA, whose economy was simultaneously disrupted by both the COVID-19 pandemic and the arrival of a second headquarters for Amazon.

Supplementary information: The online version contains supplementary material available at 10.1007/s41109-022-00487-7.

Keywords: Co-occurrence; Complexity theory; Labor retraining; Occupations; Skills.

Fig. 1

Distribution of occupational proximities $P_{S\to T}$. The distribution is approximately symmetric with mean = 0.45 and standard deviation = 0.189. Note that each occupation pair will have two proximities depending on which is the starting occupation S and which is the target T

Fig. 2

Occupation locations of (A) ${\mathcal{N}}_S$ and (B) ${\mathcal{N}}_T$ within the full skills network $\mathcal{G}.$ Here the starting occupation S is “Waiters and Waitresses” and the target occupation T is “Computer User Support Specialist”. Skills present in ${\mathcal{N}}_S$ and ${\mathcal{N}}_T$ are highlighted while those absent are greyed out. Though negative link values are used to calculate occupational proximity $P_{S\to T}$, they are excluded from these visualizations, which were rendered in Pajek using the Kamada-Kawaii algorithm