Impact of Machine Learning Algorithms on Targeted Advertising Performance Across Social Platforms
Main Article Content
Abstract
The rapid expansion of social media platforms has amplified the utilization of targeted advertising as a principal digital marketing tactic. As user-level interaction data becomes more accessible, machine learning algorithms have become essential for enhancing advertising success via precise predictions of user engagement and tailored content distribution. This research examines the influence of several machine learning algorithms on the efficacy of targeted advertising on social media platforms. A comparative experimental framework is established using structured advertising datasets that include user demographics, history interaction, advertisement characteristics, and platform environment. Various machine learning models, including Logistic Regression, Support Vector Machine, Random Forest, Gradient Boosting Machine, and Artificial Neural Network, are used and assessed utilizing essential advertising performance indicators such as click-through rate and categorization accuracy. The findings indicate that ensemble and boosting-based models routinely surpass baseline linear methods, attaining statistically significant enhancements in advertising efficacy. The results indicate that algorithmic performance differs across platform types, highlighting the need of platform-specific model selection. This research offers actionable information for marketers and digital marketing managers, while also bringing empirical proof to the expanding literature on machine learning-based targeted advertising.