By Siddharth Engineer

A skill relatedness network is an interconnected system which shows similarities between industries.

Imagine there are many employees who transition from industry A to industry B. This would suggest that the two industries require similar skillsets. A skill-relatedness network provides a broad view of such labor flows to better understand the similarities between fields.

This can be valuable information to economists, firms seeking to leverage human capital, and people seeking employment opportunities. Let us look at one example a little bit more closely. Labor mobility, referring to a worker’s ability to move between jobs and industries, is critical in the personal/financial growth of workers. This can lead to reductions in poverty and an overall stronger economy.

Transportation Limits Worker Mobility in Columbia

In Colombia, an analysis of transportation systems revealed that commute times were significantly limiting the ability of firms to make use of a diverse pool of skills.

When employers in similar industries are grouped geographically, this limits labor mobility because workers with limited transportation options cannot move between industries. Instead, we can map skill-relatedness networks to geographic regions to capture the employment opportunities that sector classifications would otherwise overlook (O’Clery et al. 2019).

Below: an example skill relatedness network for labor markets

Looking at Skill Relatedness Networks Differently

More recently, we have been able to apply skill-relatedness networks to innovation. Let us adapt our prior definition of skill-relatedness. Instead of focusing on employees who change work, let us look at inventors who change fields. At the end of the day, both employment and patents are applications of an individual’s skill. By identifying inventors with patents in multiple fields, we can get a better picture of the human capital available for innovation specifically.

Using PatentsView's disambiguated inventor data, we can mathematically define this new skill-relatedness network. Imagine transition matrices (F) between technologies of dimensions N x N where N represents the total number of technologies. Each element F_i,j = 1 if an inventor transitioned from technology i to technology j.

A Case Study

Sergio Palomeque constructed a skill-relatedness network by aggregating these matrices, comparing it to a null model, and normalizing the data. The results revealed that the diameter of the network has decreased over time, particularly in the last 10 years.

A decreasing diameter indicates more links between existing technologies than new ones are being introduced. While the reasons for this trend are still unclear, further research in skill-related networks could offer valuable insights into innovation, as demonstrated in the context of transportation in Colombia.