VISUAL ANALYTICS OF NETFLIX: UNDERSTANDING USER BEHAVIOR AND STREAMING DATA
This project delivers a comprehensive analysis of Netflix’s platform by examining both userbase metrics and content-level metadata, using datasets obtained through web scraping techniques. The analysis explores user demographics, subscription behavior, and device usage alongside insights into Netflix’s content catalog including movie titles, genres, and release patterns. The objective is to generate actionable insights through interactive visualizations and data storytelling using the R programming language. The project follows a structured methodology beginning with the extraction of user and content data from online sources. After cleaning and preprocessing with libraries such as tidyverse, lubridate, and dplyr, both datasets were integrated and explored using descriptive statistics and visual analytics. Key areas of investigation included subscription type trends, age and gender segmentation, device preferences, regional distribution of users, content genre popularity, release year trends, and correlations between content type and user demographics. Advanced visualizations were created using ggplot2, plotly, and other R-based libraries to deliver intuitive, interactive graphs and charts that communicate the underlying patterns within the data. These visualizations provide valuable perspectives on viewer behavior, content engagement, and platform performance. The study demonstrates how web-scraped data, when paired with open-source analytics tools, can uncover deep insights into digital media consumption. The results support data-driven decision-making in areas such as personalized recommendations, content acquisition, and market segmentation. Future work may incorporate machine learning techniques for predictive analytics and real-time trend monitoring. Keywords: Netflix Analytics, Web Scraping, R Programming, Data Visualization, Content Metadata, User Behavior, Subscription Trends, ggplot2, plotly, Genre Analysis, Streaming Intelligence.
Institutions
- Dr. Reddy's Laboratories (United States) (US)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-05-20
- DOI
- https://doi.org/10.5281/zenodo.15541045
- Primary Topic
- Data Visualization and Analytics
- Type
- article
- Field-Weighted Citation Impact
- 0.00