OPTIMIZING VIDEO CONTENT CREATION FOR STREAMING PLATFORMS USING BAYESIAN OPTIMIZED SUPPORT VECTOR MACHINES

Abstract

The growing demand for personalized content on streaming platforms has led to the integration of advanced artificial intelligence (AI) techniques for enhancing video content generation. This paper proposes a novel approach to optimizing video content creation by combining Generative AI with Bayesian Optimized Support Vector Machines (SVM). The proposed system uses Bayesian Optimization to fine-tune the hyperparameters of generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), alongside an SVM model for content classification based on user preferences. The aim is to automate the video creation process, reducing computational complexity while improving the relevance and quality of generated content. Experimental results demonstrate that the Bayesian Optimized SVM outperforms traditional methods in terms of accuracy, F1-score, and user engagement metrics like click-through rate (CTR). The paper highlights the potential of this framework to revolutionize real-time, personalized video generation on streaming platforms.