The Labor Space
Wages, unemployment, and the impact of automation at different locations and sectors are emerging as major challenges in modern economies. The consistently dynamic challenge of improving employment ratios and wage earners’ conditions in different locations within a city requires continuous analysis and adjustment. Moreover, the recent developments in automation have added an additional layer of complexity to this challenge and created an additional variable that is ever-changing—and devastating, if not anticipated. Thus, the challenge is improving the status quo and predicting and planning for a future with unpredictable challenges.
What we did
By collecting large and diverse data sets from a wide variety of sources within different cities and companies, combined with the use of various techniques from network science, recommender systems, and machine learning, our technology predicted (with a very high degree of accuracy) and suggest various recommendations within the labor market (for different scales, e.g., individual, company, or nation) across both space and time. First, we constructed a network map of the structure of the labor force, then analyzed how people, cities (labor forces), and neighborhoods move around in this network and predicted what they might do and what they should do to optimize their paths. Finally, we aggregated all our approaches and methods into a tool that individuals and decision-makers alike use to navigate the labor market.
The produced outcomes first included a report of the findings and recommendations based on the specified set of questions given by the stakeholder for each of the selected fine-grained locations. Also provided was a spatial labor platform that combines the various analytics and projections to produce a decision support system that truly informs decision-makers and individuals alike on maneuvering the labor market. For instance, it predicts which possible jobs an employee might take after their current job and in what location, in addition to the skills they need to acquire to make that jump. Also, if an employed individual entered the skills they already possess, the tool makes an optimal set of recommended jobs for them. For decision-makers, it helps them better understand their cities’ labor forces and predict possible dynamics, such as the impact of automation, in addition to suggesting the optimal training programs for their labor forces at different locations.