PREDIKSI CLICK-THROUGH RATE UNTUK OPTIMASI BIDDING IKLAN DIGITAL MENGGUNAKAN ALGORITMA
DOI:
https://doi.org/10.35145/jmapteksi.v8i2.6174Keywords:
Click-through Rate , Machine Learning, Digital AdvertisingAbstract
Click-Through Rate (CTR) is a key metric in digital advertising used to evaluate campaign effectiveness and support bidding strategy decisions. Conventional bidding strategies are generally static and do not consider variations in click probability across ad impressions, leading to potential cost inefficiencies. This study aims to develop machine learning models to predict CTR probabilities and analyze their application in optimizing digital advertising bidding strategies. This research utilizes the publicly available Shopping Mall Paid Search Campaign Dataset, which is aggregate in nature. Several machine learning algorithms, including Logistic Regression, Random Forest, and XGBoost, are applied to model click probability based on pre-bidding features. Model performance is 1 evaluated using probabilistic metrics such as AUC ROC, Brier Score, and calibration curve analysis. Furthermore, predicted CTR values are employed in a threshold-based bidding simulation to assess advertising cost efficiency. The results indicate that the XGBoost model provides more stable and well-calibrated probability estimates compared to other models. The bidding simulation demonstrates that CTR prediction can significantly reduce advertising budget waste, although positive profitability has not yet been achieved. Therefore, this study serves as a proof-of-concept for applying machine learning to optimize digital advertising bidding strategies.
Downloads
References
Assel, M., Sjoberg, D. D., & Vickers, A. J. (2017). The Brier score does not evaluate the clinical utility of diagnostic tests or prediction models. Diagnostic and Prognostic Research, 1(1), 1–7. https://doi.org/10.1186/s41512-017-0020-3
Bosnic, Z. (2015). ROC analysis of classifiers in machine learning : A survey ROC Analysis of Classifiers in Machine Learning : A Survey Technical report MM-1 / 2011. July. https://doi.org/10.3233/IDA-130592
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13-17-Augu, 785–794. https://doi.org/10.1145/2939672.2939785
Liu, M., Hu, Z., Lai, Z., Zheng, D., & Nie, X. (2022). Real-time Bidding Strategy in Display Advertising: An Empirical Analysis. http://arxiv.org/abs/2212.02222
Liu, Z.-P. (2013). Logistic Regression. In W. Dubitzky, O. Wolkenhauer, K.-H. Cho, & H. Yokota (Eds.), Encyclopedia of Systems Biology (pp. 1142–1143). Springer New York. https://doi.org/10.1007/978-1-4419-9863-7_396
Park, S. H., Goo, J. M., & Jo, C. H. (2004). Receiver operating characteristic (ROC) curve: Practical review for radiologists. Korean Journal of Radiology, 5(1), 11–18. https://doi.org/10.3348/kjr.2004.5.1.11
Qin, C. (2016). Empirical Research on How Keyword Advertising Linked Item Characteristics Affect CTR. International Journal of Hybrid Information Technology, 9(5), 419–430. https://doi.org/10.14257/ijhit.2016.9.5.36
Rainio, O., Teuho, J., & Klen, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 1–14. https://doi.org/10.1038/s41598-024-56706-x
Ruczinski, I., Kooperberg, C., & LeBlanc, M. (2003). Logic Regression — Methods and Software. 1024, 333–343. https://doi.org/10.1007/978-0-387-21579-2_21
Wang, J., Zhang, W., & Yuan, S. (2017). Display advertising with real-time bidding (RTB) and behavioural targeting. Foundations and Trends in Information Retrieval, 11(4–5), 297–435. https://doi.org/10.1561/1500000049
Wu, C., Heidari, M., Grama, A., & Szpankowski, W. (2023). Regret Bounds for Log-loss via Bayesian Algorithms.
