You are tasked with improving the user engagement on a digital publishing platform that caters to a diverse and demanding audience. The platform allows users limited free access to articles before requiring a paid subscription. Your goal is to recommend articles that align with individual user interests to increase subscription rates. Considering the platform's large dataset of user interactions and article content, which of the following machine learning models would be most effective for generating personalized article recommendations? Choose the best option.

Real Exam

Convolutional Neural Network (CNN), primarily used for image classification tasks.

2.5%

Hierarchical Clustering, which groups similar articles based on content but does not account for individual user preferences.

10.0%

Autoencoder and self-encoder, mainly utilized for dimensionality reduction and feature learning.

0.0%

Collaborative filtering using Matrix Factorization, which leverages user interaction data to predict preferences based on similarities between users.

45.0%

A combination of Content-based filtering and Collaborative filtering to utilize both article content and user interaction data for recommendations.

42.5%

Google Professional Machine Learning Engineer