Feature Engineering of Click-through-rate Prediction for Advertising

  • Jie RenEmail author
  • Jian Zhang
  • Jing Liang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 517)


We present the problem of click-through-rate (CTR) for search advertising in ALiMaMa, which displays user information, item information, shop information and trade results. Traditionally, people use logistic regression (LR) to predict it. However, because of the lack of learning ability and the sparse feature matrix, the prediction results are always not so satisfying. In this paper, we mainly propose some feature engineering methods based on gradient boosting decision tree (GBDT) and Bayesian smoothing to obtain a wonderful feature, which has more useful information and is not so sparse. Also, we use xgboost (XGB) instead of LR as our prediction model. The proposed methods are evaluated using offline experiments and the experiment results prove that the log loss drop near \(5\%\) after using these feature engineering methods and XGB. Obviously, it is an excellent performance.


CTR Feature engineering GBDT Bayesian smoothing XGBoost 



This work was supported by the National Natural Science Foundation of China (61671138, 61731006), and was partly supported by the 111 Project No. B17008.


  1. 1.
    Discover Feature Engineering, How to Engineer Features and How to Get Good at It.
  2. 2.
    Bowers, S., et al.: Practical lessons from predicting clicks on ads at Facebook. In: Eighth International Workshop on Data Mining for Online Advertising. ACM, pp. 1–9 (2014)Google Scholar
  3. 3.
    He, X., Chua, T.S.: Neural factorization machines for sparse predictive analytics. In: The, International ACM SIGIR Conference. ACM, pp. 355–364 (2017)Google Scholar
  4. 4.
    Mcmahan, H.B., Holt, G., Sculley, D., et al.: Ad click prediction: a view from the trenches. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, pp. 1222–1230 (2013)Google Scholar
  5. 5.
    Sukhbaatar, S., Szlam, A., Weston, J., et al.: End-to-end memory networks. Comput. Sci. (2015)Google Scholar
  6. 6.
    Cheng, H.T., Koc, L., Harmsen, J., et al.: Wide and deep learning for recommender systems, 7–10 (2016)Google Scholar
  7. 7.
    Shan, Y., Hoens, T.R., Jiao, J., et al.: Deep crossing: web-scale modeling without manually crafted combinatorial features. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, pp. 255–262 (2016)Google Scholar
  8. 8.
    Wang, X., Li, W., Cui, Y., et al.: Click-through rate estimation for rare events in online advertising. Online Multimed. Adv. Tech. Technol. (2011)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.University of Electronic Science and Technology of ChinaChengduChina

Personalised recommendations