Use cases

Gap between labor supply and demand: 40,000 first jobs

Between 2015 and 2018, the 40.000 first jobs program created by the National Government operated, which consisted of economic support for companies equivalent to at least 50% of the labor costs derived from hiring young people (18 to 28 years old) for up to one year with little or no work experience.

During the program, there were several vacancies registered in the program that were not filled and several young people enrolled in the program were not hired. For this reason, this study had the objective of studying the gaps between labor demand and supply in the context of the program. This work was carried out within the framework of an impact evaluation project of the program, conducted jointly with Econometría Consultores and SEI Consultores.

Approach

Using text mining and natural language processing, the gaps between labor supply and demand in the context of the program were studied. In particular, the Latent Dirichlet Allocation (LDA) topic model was used. Two text samples were available: job descriptions and resumes. The topic model was trained on the resumes and then applied to the job descriptions to compare the texts representing labor demand and supply in the same vector space. Subsequently, through the composition of the topics and the Euclidean distance between the texts, the gaps between what the young people offered and what the companies demanded from them were identified by qualitatively analyzing each topic.

Results

Other projects

In Projects, you can learn about real applications of our services, use cases and examples of them.

Pensiones1

Contractual Design for the Management of FONPET

Energia_electrica

Systemic Risk of Electricity Supply

planes-desarrollo1

Inventory Logistics - Multimodal Transportation

transporte_multimodal1

Integrated Development Plans

estrategia_de_deuda_banner

Ministry of Finance and Public Credit (MHCP) defines a Debt Management Strategy

reportes

Asset Allocation Model in an insurance company