SURVEY ON AI-DRIVEN REAL-TIME SCHEDULING FOR LINEAR TV BROADCASTING: A DATA-DRIVEN APPROACH

Abstract

The evolution of television broadcasting and the increasing demand for personalized content delivery have driven the need for intelligent scheduling solutions. Traditional linear TV broadcasting depends on static schedules, which often fail to adapt to real-time audience preferences and emerging viewing trends. The integration of Artificial Intelligence (AI) in real-time TV scheduling offers a transformative solution by optimizing programming decisions dynamically. This paper surveys AI-driven approaches in TV scheduling, audience analytics, and real-time engagement prediction, focusing on techniques such as Long Short-Term Memory (LSTM) networks and Grey Wolf Optimizer (GWO)-based Q-learning. The review discusses how AI leverages historical viewership data, social media trends, and external influencing factors to improve audience engagement, advertisement revenue, and broadcasting efficiency. Additionally, the survey explores the ethical and technical challenges in AI-driven broadcasting, including bias in predictive models and computational scalability.