Predictive Analytics In Sports For Transgender Lifestyle Enhancement: A Machine Learning Work

Abstract

Transgender people can improve their physical and mental health by changing their lifestyle through sports and activities. Personalized therapies made to meet their particular needs, however, are still not well studied. The present research examines how playing sports affects the lifestyle improvements of transgender people using machine learning and predictive analytics (PA). This work creates models that forecast which sports activities are best for improving lifestyle by gathering and analyzing data on performance indicators, social engagement, mental health, and physical health measurements. To categorize and suggest the best sports-based solutions, the suggested framework uses supervised learning (SL) algorithms such as decision trees (DT), random forests (RF), Support Vector Machine (SVM) and Artificial (NN) neural networks (ANN). The findings indicate that there are relationships between sports engagement, mental resilience and community integration, highlighting the potential of AI-driven personalisation in promoting wellbeing and inclusivity. Findings from this work, relying on data, can be used by policy makers as well as sports groups and health care professionals to create inclusive, supportive sport for transgender people. These results highlight the importance of accessibility and inclusivity in sport participation. Furthermore, in the field of sport science, the health of transgender people, it connects with the ongoing debate regarding the use of ML. The best accuracy of RF model is obtained at 88.1% and the performance indices are validated with it.