Palak Gupta👋
Turning data into insights with my Strategic Data Analysis
Portfolio Project 5:
Netflix Data Analysis
Overview
The Netflix Data Analysis project focused on exploring global viewing trends, content patterns, and platform usage using a dataset of movies and TV shows available on Netflix. The objective was to understand user preferences, content popularity, and release strategies to uncover insights that could benefit content creators, marketers, and data analysts interested in the entertainment domain.
Research: The research phase involved studying how Netflix curates content across countries, the type of content preferred by different audiences (genre, rating, release year), and how Netflix’s original productions impact viewer engagement. Additional attention was paid to understanding seasonal content trends and user ratings.
Information Architecture: The dataset was structured with fields like title, type (Movie/TV Show), director, cast, country, release year, date added, duration, genre (listed_in), and rating. After cleaning and preprocessing, the data was ready for exploratory analysis and visual storytelling.
Wireframing and Prototyping: A dashboard prototype was created in Power BI/Tableau, enabling users to filter content by year, country, genre, and type. It included KPIs like content count by year, country-wise content distribution, and genre-wise popularity. Interactive graphs and heatmaps were added to highlight binge-worthy periods and content gaps.
Challenges
Missing and Inconsistent Data:
- Challenge:Many entries lacked director or cast information; country data was missing for some shows.
- Solution:Used imputation strategies and visual flags for incomplete data while focusing analysis on fields with the most integrity.
Genre Categorization:
- Challenge: Shows often belonged to multiple overlapping genres, making aggregation and filtering difficult.
- Solution:Split multi-genre entries and used one-hot encoding to analyze each genre's frequency and trend independently.
Temporal Trend Analysis:
- Challenge:Detecting content addition patterns over time to identify Netflix’s content strategy.
- Solution: Created time-series plots based on date_added and compared it with release_year to analyze Netflix’s acquisition vs. production balance.
Country-wise Comparisons:
- Challenge: Normalizing content counts across countries with vastly different Netflix libraries.
- Solution:Used percentage-based comparisons and per capita content metrics to ensure fairness in analysis.
Results/Conclusion:
The analysis revealed that Netflix has been increasingly investing in original TV content since 2018, with noticeable peaks in content addition during the pandemic period. The U.S., India, and the U.K. contributed the most content, while genres like drama, comedy, and documentaries dominated the platform. Time-based insights showed Netflix tends to release high volumes of content during Q4, likely for year-end engagement. The findings provided strategic value for content recommendation engines, marketing teams, and cultural trend analysts. Future steps could involve incorporating user rating data and watch-time metrics for deeper behavioral analysis..
