Film Box Office Success Forecasting: A Genre-Driven Classification System Using Machine Learning and Cluster Analysis

Predicting the box office success of films remains a formidable challenge, influenced by numerous factors such as genre, marketing endeavors, and audience preferences. In this paper, a genre-centric classification system employing machine learning and cluster analysis techniques is introduced to forecast the box office performance of movies. A comprehensive dataset comprising diverse features including genre, cast, crew, budget, and release timing is utilized. Through the utilization of machine learning algorithms, specifically decision trees, random forests, support vector machines, regressions, and neural networks, patterns and correlations between film attributes and box office success are discerned. Additionally, employing cluster analysis enables classification of films with akin characteristics, facilitating the identification of genre-specific trends. Empirical findings validate the efficacy of the proposed methodology in accurately predicting the box office performance of films across various genres. This research contributes to the progression of predictive modeling in the film industry, offering actionable insights for filmmakers, distributors, and investors to optimize strategies for maximizing box office revenue.