Algorithmic Marketing: Consumer Targeting, Optimization, and Performance Outcomes

Abstract

Algorithmic marketing has become a critical component of digital advertising, enabling organizations to leverage artificial intelligence (AI), data analytics, and automation to improve targeting precision and campaign effectiveness. This study examines the influence of consumer-targeting characteristics and advertising optimization factors on marketing performance outcomes within an algorithmic marketing framework. Using a quantitative research design, secondary data comprising 9,854 advertising observations were analyzed. Consumer-targeting variables included age, gender, income, and location, while advertising optimization factors comprised ad type, ad topic, and ad placement. Marketing performance was assessed using clicks, click-through rate (CTR), and conversion rate. Multiple linear regression and Random Forest analyses were employed to evaluate explanatory and predictive relationships among the variables. The findings revealed that consumer-targeting and optimization-related factors did not significantly influence CTR or conversion rate, with both regression models exhibiting limited explanatory power (R² = 0.002). Similarly, the Random Forest model demonstrated weak predictive performance (R² = -0.085), indicating that the selected variables explained only a small proportion of advertising outcomes. Feature importance analysis identified income and age as the most influential predictors, although their overall contribution remained limited. The results suggest that advertising performance is likely shaped by additional factors, including consumer behavior, contextual influences, platform algorithms, and real-time engagement dynamics. This study contributes to the algorithmic marketing literature by highlighting the limitations of demographic targeting and basic optimization variables and emphasizing the need for more comprehensive, data-rich approaches to understanding digital advertising effectiveness.