Prototipo web para la recomendación de ofertas de empleo basado en análisis de contenido

Abstract

Digital transformation has significantly impacted multiple sectors of the global economy, including the labor market. In this context, information systems have been developed to serve as intermediaries between organizations and prospective employees. Several widely used platforms, such as LinkedIn, Indeed, and Glassdoor, provide job recommendations to registered users by considering feedback from other users with similar characteristics. Other platforms employ alternative recommendation strategies, including tag-based and keyword-based approaches, among others. However, such recommendations may at times become irrelevant due to biases associated with premium subscription models, high platform reputation, or the suggestion of job offers in entirely unrelated fields that nevertheless share overlapping terminology in different contexts. To address this issue, the present study proposes the development of a web-based prototype designed to recommend job opportunities through the application of machine learning techniques, specifically content-based recommendation. The proposed system utilizes user profile information and job offer attributes as primary data sources, with the aim of generating more relevant and personalized recommendations tailored to individual user needs.