Click here to access project demo video

Description: The rapid expansion of short-form video platforms has fundamentally transformed digital content consumption, creating a highly competitive attention economy. Despite the massive scale of these platforms, creators frequently struggle to navigate opaque, black-box recommendation systems, relying on unguided trial-and-error rather than empirical data. The motivation for this research stems from the critical need to bridge the gap between qualitative cultural studies of content creation and technical predictive modeling. This project leverages large-scale, real-world platform data, specifically utilizing Kaggle datasets, to extract and test technical variables against genuine human interactions. By employing a Python-based machine learning pipeline utilizing Pandas and Scikit-Learn, this study transitions the focus from psychological descriptions to technical predictions. The ultimate benefit of this approach is the delivery of a robust, empirically backed framework, deployed as an interactive Streamlit dashboard, that replaces intuitive guesswork with data-driven engagement optimization, providing actionable insights for creators to maximize their algorithmic visibility.