Novel Tools for Monitoring Process Quality: Detection of Anomalies in Digital Data on Content Consumption Using the DBSCAN Clustering Method

Novel Tools for Monitoring Process Quality: Detection of Anomalies in Digital Data on Content Consumption Using the DBSCAN Clustering Method

The article describes a step-by-step algorithm for the method of selecting optimal DBSCAN clustering parameters based on analyzing the silhouette score and automatically determining its elbow point, as well as the results of its application to data on content consumption by users of one of the leadi...

Full description

Saved in:
Bibliographic Details
Published in:Russian engineering research Vol. 44; no. 9; pp. 1370 - 1374
Main Authors: Mosin, V. G., Kozlovskii, V. N., Nenashev, M. V.
Format: Journal Article
Language:English
Published: Moscow Pleiades Publishing 2024
Springer Nature B.V
Subjects:
Algorithms
Clustering
Consumption
Digital data
Engineering
Engineering Design
pandas
quality management
data analysis
scikit-learn
DBSCAN
clustering
numpy
machine learning metrics
silhouette score
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The article describes a step-by-step algorithm for the method of selecting optimal DBSCAN clustering parameters based on analyzing the silhouette score and automatically determining its elbow point, as well as the results of its application to data on content consumption by users of one of the leading hosting services.
ISSN:1068-798X
1934-8088
DOI:10.3103/S1068798X24702137