Digital Transformation and Administration Innovation 4 Serial Number 14 2026 07 01 Predicting Digital Marketing Performance Based on Content Quality, Engagement Rate, and Targeting Precision Using Artificial Intelligence Predicting Digital Marketing Performance Based on Content Quality, Engagement Rate, and Targeting Precision Using Artificial Intelligence 1 10 10.61838/dtai.258 EN Journal Article 2026 01 05 <p>The objective of this study is to predict digital marketing performance based on content quality, engagement rate, and targeting precision using artificial intelligence. This study employed a quantitative, applied, correlational design with a sample of 312 digital marketing professionals, social media managers, and online business owners from Tehran, selected through stratified random sampling. Data were collected using a combination of researcher-developed questionnaires and objective performance metrics extracted from digital platforms, measuring content quality, engagement rate, targeting precision, and digital marketing performance. The reliability and validity of the instruments were confirmed through Cronbach’s alpha and expert panel review. Data analysis was conducted using SPSS version 27 for descriptive statistics, Pearson correlation, and multiple regression analysis, while artificial intelligence models, including artificial neural networks and random forest algorithms, were implemented using Python-based tools to enhance predictive accuracy. Model performance was evaluated using indicators such as R², RMSE, and cross-validation techniques. The results revealed that content quality, engagement rate, and targeting precision all have significant positive effects on digital marketing performance (p &lt; 0.001). The multiple regression model explained 61% of the variance in performance (R² = 0.61), indicating strong predictive power. Among the predictors, content quality emerged as the strongest contributor, followed by engagement rate and targeting precision. Artificial intelligence models demonstrated superior predictive performance compared to traditional regression, with the artificial neural network achieving the highest explanatory power (R² = 0.74), followed by the random forest model (R² = 0.71). These findings confirm the robustness of AI-based approaches in capturing complex, nonlinear relationships among digital marketing variables. The study concludes that digital marketing performance can be effectively predicted through a combination of content quality, engagement rate, and targeting precision, particularly when analyzed using artificial intelligence techniques. The integration of AI enhances predictive accuracy and provides deeper insights into the dynamics of marketing performance, offering valuable implications for both researchers and practitioners seeking to optimize digital marketing strategies in competitive environments.</p> https://www.journaldtai.com/index.php/jdtai/article/download/258/258