<p>Due to increasing competition and evolving viewer preferences, content creators on YouTube face challenges in optimizing revenue generation. To address these challenges, this study proposes a novel framework comprising three algorithms namely, Similar Channels algorithm, Rank Score algorithm, and Video Analysis algorithm with Long Short-Term Memory. The Similar Channels algorithm introduces a multidimensional similarity assessment that integrates content features, video tags, and engagement metrics such as likes, views, and subscribers for accurately identifying the channels with comparable performance and audience engagement. In addition, the Similar Channel algorithm dynamically adjusts weightage for different metrics based on content type. The Rank Score algorithm enhances competitor analysis by implementing a weighted ranking system that assigns adaptive weights to engagement metrics, providing creators with actionable insights into their competitive landscape. The Video Analysis algorithm employs a Long Short-Term Memory-based Recurrent Neural Network to capture temporal trends in engagement metrics and effectively identify the top-performing videos that drive audience engagement and revenue. Further, the Video Analysis algorithm leverages sequential engagement data to predict video success with greater accuracy. Experimental evaluations demonstrate the effectiveness of the proposed algorithms, achieving a high ranking accuracy of 0.98 for competitor channel analysis and precisely identifying top-performing videos based on engagement scores. By leveraging big data analysis and novel algorithmic improvements, content creators optimize revenue generation on YouTube channels by making data-driven decisions. The Similar Channel and Rank Score algorithms provide insights into competitor performance, while the Video Analysis algorithm with Long Short-Term Memory enables the identification of top-performing videos.</p>