Labor perception of the tourism sector using machine learning in the Puno region, 2024.

Abstract

The tourism sector is a dynamic and diverse industry that faces constant challenges in human resource management and job satisfaction. In this article, we present an innovative approach to understand job perception in the tourism sector using machine learning techniques. Using data collected from surveys applied to workers in the tourism sector, an analysis with Machine Learning algorithms to classify and predict various aspects of job perception, such as job satisfaction, employee loyalty and the probability of job turnover. Our study highlights the importance of using advanced computational approaches to better understand the complexities of the workforce in the tourism sector and provide valuable information for strategic decision making in human resource management. Gender diversification of men and women among its staff is not actively encouraged. Salary discrepancies are evident between men and women who perform identical or similar functions, strategies are not implemented to promote diversity and gender equality, nor are manifestations of prejudices avoided between the variables and indicators that contribute to the Tree model. Decisions are gender, sub-sector and the indicators are: there are no clear opportunities for positions without gender preference; gender diversification of men and women among its staff is not actively encouraged; but they do show salary discrepancies between men and women who perform identical or similar functions; Strategies to promote diversity and gender equality are not implemented, nor are manifestations of prejudice avoided; while in Random Forest the key variables are gender, position, subsector and length of service, along with the indicators that stand out are: there are no clear opportunities for positions without gender preference and the company's business culture offers a greater number of opportunities for men.