Comparative study on post-workout meal recommender systems using machine learning algorithms

The abundance of options for post-workout healthy meal recommendations can be overwhelming, it becomes crucial to streamline, prioritize, and effectively provide pertinent information. This is necessary to address the issue of information overload and the consequent development of unhealthy eating habits, which has become a significant concern for numerous Internet users. The discipline of fitness and nutrition has recently seen an increased emphasis on post-workout meal optimisation to improve athletic performance and support muscle recovery. The post-workout meal recommender systems described in this study use machine learning algorithms to offer individualised food recommendations. To provide precise and customised suggestions, the suggested methods include content-based filtering, collaboration-based filtering, and a hybrid approach. The results of this study can be used to inform the development of food recommendation systems, as well as to guide food businesses in making decisions about their offerings. Diets with higher mean occurrence indicate that more people are interested in such diets after a workout. At the same time, macro-nutrients with higher mean occurrence indicate what nutrients are popular after a workout among people with similar health routine. In the future, it would be beneficial to expand the scope of this study to include a more diverse population, as well as to incorporate additional factors such as dietary restrictions and nutritional information.