YouTube Streamer Analysis

This project focuses on building a Content Recommendation System for YouTube users based on streamers' performance metrics and user preferences. It aims to enhance the user experience by suggesting channels and videos that align with the user’s watch history and preferred categories.

Features

• Rank: The ranking of the YouTuber.
• Username: The name of the YouTube channel.
• Categories: The content categories (some entries are missing).
• Subscribers: The number of subscribers (in float format).
• Country: The country where the channel is based.
• Visits: The total visits to the channel.
• Likes: The total likes on the channel's videos.
• Comments: The total number of comments.
• Links: The URL link to the YouTube channel.

Guidelines for Project Components:

1.DATA EXPLORATION

• Start by exploring the dataset to understand its structure and identify key variables.
• Check for missing data and outliers.

2.Finding Outliers using Boxplot

3.Trend Analyisis

• Identify trends among the top YouTube streamers. Which categories are the most popular?
• Is there a correlation between the number of subscribers and the number of likes or comments?
• correlation
• 

4.Audience Study

• Analyze the distribution of streamers' audiences by country. Are there regional preferences for specific content categories?

5.Performance Metrics

• Calculate and visualize the average number of subscribers, visits, likes, and comments.
• Are there patterns or anomalies in these metrics?
• 

6.Content Categories

• Explore the distribution of content categories. Which categories have the highest number of streamers?
• Are there specific categories with exceptional performance metrics?

7.Brands and Collaborations

• Analyze whether streamers with high performance metrics receive more brand collaborations and marketing campaigns.
• 

8.Benchmarking

• Identify streamers with above-average performance in terms of subscribers, visits, likes, and comments.
• Who are the top-performing content creators?

9.Content Recommendations

-Propose a system for enhancing content recommendations to YouTube users based on streamers categories and performance metrics

-Design and implement a recommendation system that suggests channels and videos based on User's watch history and preferred categories and Streamer performance within those categories.

Usage

1. Run the notebook: Open the YT_Streamer.ipynb in Jupyter and run each cell to load the data, process it, and generate recommendations.
2. Modify recommendations: You can tweak the recommendation logic by adjusting the performance metrics or filtering criteria in the code.

Contact

For any questions or issues, feel free to reach out to [sriramkannanofficial@gmail.com] or open an issue on GitHub.