Personalized Recommendation and Consumer Conversion: Evidence from Commercial Advertising Data
DOI:
https://doi.org/10.64549/jaai-ii.v1i2.122Keywords:
Personalization, Recommendation systems, Advertising, Conversion prediction, DeepFM, Explainable AIAIGC, Traditional cultureAbstract
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.
References
Adomavicius, G. and Tuzhilin, A., 2005. Toward the next generation of recommender systems. IEEE TKDE, 17(6), 734–749. https://doi.org/10.1109/TKDE.2005.99
Arellano, M. and Bond, S., 1991. Some tests of specification for panel data. Review of Economic Studies, 58(2), 277–297. https://doi.org/10.2307/2297968
Baron, R. M. and Kenny, D. A., 1986. The moderator–mediator variable distinction. JPSP, 51(6), 1173–1182. https://doi.org/10.1037/0022-3514.51.6.1173
Breiman, L., 2001. Random forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324
Cao, L., 2017. Data science: A comprehensive overview. ACM Computing Surveys, 50(3). https://doi.org/10.1145/3076253
Chapelle, O., Manavoglu, E. and Rosales, R., 2014. Simple and scalable response prediction for display advertising. ACM TIST, 5(4). https://doi.org/10.1145/2532128
Chen, T. and Guestrin, C., 2016. XGBoost. KDD ’16, 785–794. https://doi.org/10.1145/2939672.2939785
Cheng, H.-T., et al., 2016. Wide & deep learning for recommender systems. DLRS ’16, 7–10. https://doi.org/10.1145/2988450.2988454
Covington, P., Adams, J. and Sargin, E., 2016. Deep neural networks for YouTube recommendations. RecSys ’16, 191–198. https://doi.org/10.1145/2959100.2959190
Criteo AI Lab., 2014. Display advertising challenge dataset. https://ailab.criteo.com/display-advertising-challenge-criteo/
Deng, A., et al., 2013. Improving the sensitivity of online controlled experiments by utilizing pre-experiment data. WSDM ’13, 123–132. https://doi.org/10.1145/2433396.2433413
European Union., 2016. General Data Protection Regulation. https://eur-lex.europa.eu/eli/reg/2016/679/oj
Friedman, J. H., 2001. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
Gama, J., et al., 2014. A survey on concept drift adaptation. ACM Computing Surveys, 46(4). https://doi.org/10.1145/2523813
Guo, H., et al., 2017. DeepFM: A factorization-machine based neural network for CTR prediction. IJCAI, 1725–1731. https://doi.org/10.24963/ijcai.2017/239
He, X. and Chua, T.-S., 2017. Neural factorization machines. SIGIR ’17, 355–364. https://doi.org/10.1145/3077136.3080777
Hoerl, A. E. and Kennard, R. W., 1970. Ridge regression. Technometrics, 12(1), 55–67. https://doi.org/10.1080/00401706.1970.10488634
Koenker, R. and Bassett, G., 1978. Regression quantiles. Econometrica, 46(1), 33–50. https://doi.org/10.2307/1913643
Lundberg, S. M. and Lee, S.-I., 2017. A unified approach to interpreting model predictions. NeurIPS. https://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions
McMahan, H. B., et al., 2013. Ad click prediction: A view from the trenches. KDD ’13, 1222–1230. https://doi.org/10.1145/2487575.2488200
Rendle, S., 2010. Factorization machines. IEEE ICDM, 995–1000. https://doi.org/10.1109/ICDM.2010.127
Resnick, P. and Varian, H. R., 1997. Recommender systems. Communications of the ACM, 40(3), 56–58. https://doi.org/10.1145/245108.245121
Ribeiro, M. T., Singh, S. and Guestrin, C., 2016. Why should I trust you? KDD ’16, 1135–1144. https://doi.org/10.1145/2939672.2939778
Ricci, F., Rokach, L. and Shapira, B. (Eds.)., 2011. Recommender systems handbook. Springer. https://doi.org/10.1007/978-0-387-85820-3
Rosenbaum, P. R. and Rubin, D. B., 1983. The central role of the propensity score. Biometrika, 70(1), 41–55. https://doi.org/10.1093/biomet/70.1.41
Sarwar, B., Karypis, G., Konstan, J. and Riedl, J., 2001. Item-based collaborative filtering. WWW ’01, 285–295. https://doi.org/10.1145/371920.372071
Sculley, D., et al., 2015. Hidden technical debt in machine learning systems. NeurIPS. https://papers.nips.cc/paper/5656-hidden-technical-debt-in-machine-learning-systems
Shapley, L. S., 1953. A value for n-person games. Contributions to the Theory of Games II. https://doi.org/10.1515/9781400881970-018
Sweeney, L., 2002. k-anonymity. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 10(5), 557–570. https://doi.org/10.1142/S0218488502001648
Tibshirani, R., 1996. Regression shrinkage and selection via the lasso. JRSS B, 58(1), 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Tao Luo, Ruyi Yin, Yang Guo
This work is licensed under a Creative Commons Attribution 4.0 International License.
CC Attribution 4.0