BUILDING A RATING SYSTEM BASED ON 3D VISUALIZATION OF KEY METRICS OF YOUTUBE CHANNELS

The article presents a method for building a rating system for analyzing YouTube channels using clustering in three-dimensional space. Based on the set of statistical data, a preliminary analysis was carried out, including the conversion of initial indicators, the calculation of normalized metrics (average daily views, video upload frequency, views per subscriber) and filtering of outliers. The application of the k-means algorithm (Kmeans), implemented in the Python programming language, after scaling the data, allowed 3D segmentation of channels into groups reflecting different levels of efficiency: leaders, middle and beginners. The results of the study demonstrate that the integration of calculated relationships and 3D visualization contributes to more accurate comparative analysis and identification of key patterns in the dynamics of channel development.