Machine Learning-Based Prediction of Muscle Hypertrophy: A Random Forest Approach Using Training and Nutrition Data

Muscle hypertrophy is defined as the enlargement of muscle fibers through resistance training stimulation, and remains a primary goal for many individuals engaged in structured exercise programs. However, response to training may vary significantly due to genetic, physiological, and lifestyle factors. As a result, many individuals struggle to predict whether a given training program will effectively support their muscle growth goals, often leading to inefficient training strategies and suboptimal outcomes. The lack of predictive tools that can estimate muscle hypertrophy outcomes based on mesurable variables highlights the need for data driven approaches in personal fitness planning. Therefore, this study aims to develop a Muscle Hypertrophy prediction model using the Random Forest algorithm. The data used are synthetic data generated from ChatGPT, which consists of 500 samples with 5 relevant features. Models were developed with 80% train 20% test using R2 Metrics. The results showed that the optimized Random Forest model achieved an accuracy of 79% on R2. These findings indicate that the method used can help predicting the muscle growth by measurable metrics. So it can be used as a tool in Personal Fitness goal.