Estudio de la demanda laboral de las PYMES y grandes empresas de Guayaquil.

Abstract

This research analyzes the labor demand of SMEs and large companies in Guayaquil, Ecuador, using data science as the main methodological tool. The study addresses the existing imbalance between the skills required by companies and the available workforce, in a context marked by high levels of unemployment and underemployment. Public data from the National Institute of Statistics and Census (INEC), specifically the ENEMDU survey, was processed and modeled using supervised machine learning techniques. Decision trees and Random Forest algorithms were applied in R Studio to classify and predict occupational demand, achieving an accuracy rate of 95%. Results show that the categories “Private,” “External,” and “Worker” concentrate most of the demand, while minor categories such as “Domestic,” “Unpaid,” and “Helper” remain underrepresented. The findings highlight the potential of predictive models to reduce recruitment mismatches, guide corporate strategies, and support evidence-based public policies for labor management in Ecuador.