Previsão da utilização do ambulatório de uma fábrica de calça- dos por meio de redes neurais recorrentes LSTM

Abstract

Demand forecasting is a critical problem for resource management in a factory, especially regarding inputs and the capacity of the clinic. The objective of this study was to develop a machine learning model capable of estimating the demand for medical care for employees at a large-scale factory located in the northeast region of Brazil, considering the number of visits to the factory clinic. The methodology used consists of collecting and processing historical data from the clinic, applying the LSTM technique to train and test the model, and evaluating its performance using metrics such as mean squared error. The obtained results indicate that the proposed model is capable of predicting the clinic's utilization with a certain level of accuracy, thus assisting in human resource management. This study contributes to the advancement of knowledge in the field of artificial intelligence applied to occupational health.