Predicting Physical Activity Levels for the Personalization of Well-Being Programmes

Aim: The aim of this paper is to verify whether a machine learning model can be effectively used to predict people’s physical activity levels for personalising employee well-being programmes in companies. Methodology: The following research methodologies were used in this paper: literature analysis and experiment, in the form of verification of the predictions made by the created machine learning model. Results: The results obtained from the evaluation of the model showed that the use of human characteristics data to predict physical activity levels for the personalisation of well-being programmes does not guarantee good enough results. Implications and recommendations: By effectively predicting physical activity levels, well-being programmes can be more effectively personalised to the individual needs of employees, which can contribute to improving their health. Originality/value: The literature review found that the use of machine learning to predict physical activity levels has not been described in detail in the literature.