Comparative Analysis of Logistic Regression, Random Forest, and XGBoost for Click-Through Rate Prediction in Digital Advertising

DOI

10.2991/978-94-6463-542-3_54How to use a DOI?

Keywords

Click-Through Rates; Prediction models; XGBoost

Abstract

In the current research landscape, there remain gaps in predicting Click-Through Rates (CTR) for online advertisements. The study addresses these shortcomings by scrutinising three prediction models: logistic regression (LR), random forests (RF), and extreme gradient boosting (XGBoost). This methodology involves the same preprocessing of the data for all models. The performance metrics reveal that XGBoost shows the highest accuracy. For instance, XGBoost achieved a notable accuracy percentage of 94.10%, with RF and LR at 93.52% and 93.23% respectively. XGBoost also recorded the highest area under the curve, indicating its proficiency in distinguishing clicks from non-clicks. The study goes beyond mere numbers by delving into the strengths and weaknesses of each model. While LR is prized for its simplicity and interpretability, RF is valued for its robustness and accuracy over a range of data. However, XGBoost excels at handling complex data structures more efficiently. This study provides a theoretical basis for strengthening digital marketing strategies. It can guide advertisers and platform managers to optimize marketing activities. For example, it helps develop more sophisticated prediction tools for online advertising.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jiacheng Lou
PY  - 2024
DA  - 2024/10/15
TI  - Comparative Analysis of Logistic Regression, Random Forest, and XGBoost for Click-Through Rate Prediction in Digital Advertising
BT  - Proceedings of the 2024 2nd International Conference on Management Innovation and Economy Development (MIED 2024)
PB  - Atlantis Press
SP  - 462
EP  - 470
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-542-3_54
DO  - 10.2991/978-94-6463-542-3_54
ID  - Lou2024
ER  -