A Comparative Study of OTT Market Demographic Grouping
Akshay Rai1, Arayan Kataria2, Vishnupriya3
1Akshay Rai, Department of Computer Science and Engineering, Vellore Institute of Technology University, Vellore (Tamil Nadu), India.
2Arayan Kataria, Department of Computer Science and Engineering, Vellore Institute of Technology, University, Vellore (Tamil Nadu), India.
3Dr. Vishnupriya, Department of Computer Science and Engineering, Vellore Institute of Technology University Vellore (Tamil Nadu), India.
Manuscript received on 08 April 2024 | Revised Manuscript received on 12 April 2024 | Manuscript Accepted on 15 May 2024 | Manuscript published on 30 May 2024 | PP: 1-8 | Volume-12 Issue-5, May 2024 | Retrieval Number: 100.1/ijisme.F986213060524 | DOI: 10.35940/ijisme.F9862.12050524
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This research paper aims to analyze the population and potential viewer count for different age groups, genders, and employment status in three distinct clusters of states in the United States. The clusters were formed based on demographic similarities using the K-means clustering for exploration and Hierarchical (Birch and Agglomerative) and Spectral clustering on a dataset that included information on the population, age, gender, employment status, and potential viewers for each state. The research then analyzed the clusters to determine the most significant factors contributing to the viewership in each segment and found that each cluster has unique demographic features, such as a high concentration of younger male viewers in one cluster and older female viewers in another. Additionally, the research identified the states and demographic groups with the highest potential viewership within each cluster. The results section will discuss the demographic features of each cluster, followed by an analysis of the states and demographic groups with the highest potential viewership within each cluster. Our analysis provides valuable insights into the audience’s characteristics and preferences, which can be used to optimize marketing and content strategies for the streaming service. The paper will conclude by discussing the implications of these findings and possible future directions for research.
Keywords: Demographic Segmentation, Viewer Clustering, Hierarchical Clustering, Spectral Clustering, Elbow Method, Cross-Platform Segmentation, Targeted Marketing, Cluster Validation
Scope of the Article: Clustering