Personalized Health and Lifestyle Recommendations for Women: A Comparative Analysis of General and Sequential Recommender Models

This bachelor thesis explores the efficacy and applicability of general versus sequential recommender models within a female health assistant application, aiming to enhance personalized health and lifestyle recommendations. It delves into the development and comparison of these models to ascertain which approach more effectively meets the needs and preferences of female users. By employing a dataset that encompasses a broad spectrum of female health concerns and user interactions, the study evaluates how these models perform in predicting and recommending health advice and lifestyle tips. Through quantitative analysis and user feedback, the thesis seeks to determine the best performing recommender system approach for improving user experience and outcomes in female health applications. This research contributes to the understanding of personalized health and lifestyle recommendation systems and their potential to address the nuanced needs of women in their health and wellness journeys.