Personalized Recommendation and Consumer Conversion: Evidence from Commercial Advertising Data

This study examines how AI-driven personalized recommendation relates to consumer conversion in digital advertising, using the Criteo commercial advertising dataset. Descriptive statistics, Pearson correlation, logistic regression, and DeepFM are used to analyze conversion behavior and compare predictive performance. The study reports an 11.6% conversion rate and finds that a one-unit increase in AI recommendation Match is associated with approximately 4.4% higher conversion odds (β = 0.0431, p < .01). DeepFM achieves an AUC of 0.8471 and a LogLoss of 0.3102, outperforming logistic regression (AUC = 0.6269) and random forest (AUC = 0.7249) on the principal discrimination and loss measures; its accuracy is 0.8842. Robustness analyses include an alternative CTR measure, mobile-user subsample, Probit estimation, and propensity-score matching. The study reports a positive PSM average treatment effect of 0.0427 (p < .01) and concludes that personalized matching is an important factor associated with conversion, while user activity and advertising context also contribute to conversion outcomes. The findings support the use of DeepFM for conversion prediction and motivate dynamic recommendation weighting and coordinated marketing optimization.